library(readxl)
dataset <- read_excel("~/Dataset/Dataset_IA_corte_II.xlsx")
View(dataset)EDA - Inteligencia Aritifical
En el contexto actual, los algoritmos realizados con inteliegencia artificial se han vuelto esenciales para resolver una amplia variedad de problemas, desde la clasificación de imágenes hasta la predicción de patrones complejos. Cada uno de ellos tiene un rendimiento distinto dependiendo de múltiples factores, entre ellos el tipo de framework utilizado para implementarlo y el tipo de datos sobre los que se entrena el modelo. Este análisis busca explorar estas diferencias para entender cuál framework proporciona mejores tesultados, especialemtne en términos de precisión y tiempo de entrenamiento, al trabajar con datos tabulares.
Los datos tabulares son uno de los tipos más comunes de datos utilizados en el entrenamiento de modelos de inteligencia artificial. Se organizan en filas y columnas, donde cada columna representa una característica y cada fila una observación, tal como ocurre en una hoja de cálculo. Estos datos, pueden incluir características como la edad, el ingreso, la ubicación, entre otras, y son utilizados en diversas aplicaciones industriales y académicas.
Por lo tanto, el objetivo de este análisis es responder a la siguiente pregunta: ¿Qué framework ofrece mejores resultados en términos de precisión y tiempo de entrenamiento al trabajar con datasets tabulares?. Esta pregunta permitirá evaluar el rendimiento y la eficiencia de los diferentes frameworks, identificando cuál de ellos puede ser más adecuado según las características del problema y los datos disponibles.
Para comenzar, se carga la base de datos:
Con fines ilustrativos, se hace una vista preliminar con los primeros 10 registros del dataset:
library(knitr)
print(kable(head(dataset, 10)))
|Algorithm |Framework |Problem_Type |Dataset_Type | Accuracy| Precision| Recall| F1_Score| Training_Time|Date |
|:--------------|:------------|:------------|:------------|---------:|---------:|---------:|---------:|-------------:|:-------------------|
|SVM |Scikit-learn |Regression |Time Series | 0.6618051| 0.6929447| NA| 0.4426950| 4.978592|2023-03-08 11:26:21 |
|K-Means |Keras |Clustering |Time Series | 0.7443216| 0.4900292| 0.8766533| 0.4414046| NA|2023-03-09 11:26:21 |
|Neural Network |Keras |Clustering |Image | 0.8852037| 0.5948056| 0.9685424| 0.9644707| 3.282594|2023-03-10 11:26:21 |
|SVM |Keras |Clustering |Text | 0.8416477| 0.8424142| 0.8748388| 0.7041523| 4.041629|2023-03-11 11:26:21 |
|SVM |Scikit-learn |Regression |Tabular | 0.7229514| 0.6856109| 0.3010956| 0.6456472| 3.603991|2023-03-12 11:26:21 |
|K-Means |PyTorch |Regression |Image | 0.6368133| 0.6255330| 7.4548096| 0.8865271| 3.006475|2023-03-13 11:26:21 |
|Neural Network |PyTorch |Regression |Text | 0.9985623| 0.6366858| 0.3357948| 0.9014956| NA|2023-03-14 11:26:21 |
|Neural Network |Scikit-learn |Regression |Image | 0.7130907| 0.6756681| 0.4803251| 0.5993146| 2.328345|2023-03-15 11:26:21 |
|SVM |Keras |Regression |Time Series | NA| 0.8710099| 0.3416673| 0.8161708| 3.406453|2023-03-16 11:26:21 |
|Random Forest |Keras |Regression |Text | 0.5818119| 0.9352508| NA| 0.8626737| 3.419905|2023-03-17 11:26:21 |Esta base de datos, está compuesta por un total de 560 filas y 10 columnas:
dim(dataset)[1] 560 10El dataset en cuestión, contiene 10 variables diferentes, que se definen y clasifican según sus tipos en la siguiente tabla:
# Cargar las librerías necesarias
library(knitr)
library(kableExtra)
# Crear un dataframe con las variables, sus definiciones y el tipo de variable
variables <- data.frame(
Variable = c("Algorithm", "Framework", "Problem_Type", "Dataset_Type",
"Accuracy", "Precision", "Recall", "F1_Score",
"Training_Time", "Date"),
Definición = c("Algoritmo de aprendizaje automático utilizado.",
"Framework utilizado para implementar el algoritmo.",
"Tipo de problema abordado por el modelo.",
"Tipo de datos utilizado para entrenar el modelo.",
"Precisión del modelo.",
"Proporción de verdaderos positivos sobre los ejemplos predichos como positivos.",
"Proporción de verdaderos positivos sobre los ejemplos que son realmente positivos.",
"Media armónica de la precisión y el recall.",
"Tiempo requerido para entrenar el modelo (en segundos).",
"Fecha en que se realizó la ejecución del modelo."),
Tipo = c("Cualitativa, nominal", "Cualitativa, nominal", "Cualitativa, nominal",
"Cualitativa, nominal", "Cuantitativa, continua", "Cuantitativa, continua",
"Cuantitativa, continua", "Cuantitativa, continua",
"Cuantitativa, continua", "Cualitativa, ordinal")
)
# Crear una tabla a partir del dataframe
kable(variables, format = "html", escape = FALSE, col.names = c("Variable", "Definición", "Tipo")) %>%
kable_styling(full_width = F, position = "left") %>%
add_header_above(c("Variables - Inteligencia Artificial Dataset" = 3))| Variable | Definición | Tipo |
|---|---|---|
| Algorithm | Algoritmo de aprendizaje automático utilizado. | Cualitativa, nominal |
| Framework | Framework utilizado para implementar el algoritmo. | Cualitativa, nominal |
| Problem_Type | Tipo de problema abordado por el modelo. | Cualitativa, nominal |
| Dataset_Type | Tipo de datos utilizado para entrenar el modelo. | Cualitativa, nominal |
| Accuracy | Precisión del modelo. | Cuantitativa, continua |
| Precision | Proporción de verdaderos positivos sobre los ejemplos predichos como positivos. | Cuantitativa, continua |
| Recall | Proporción de verdaderos positivos sobre los ejemplos que son realmente positivos. | Cuantitativa, continua |
| F1_Score | Media armónica de la precisión y el recall. | Cuantitativa, continua |
| Training_Time | Tiempo requerido para entrenar el modelo (en segundos). | Cuantitativa, continua |
| Date | Fecha en que se realizó la ejecución del modelo. | Cualitativa, ordinal |
Utilizando la función summary, se verifica que los tipos de datos correspondan a su respectiva columna:
summary(dataset) Algorithm Framework Problem_Type Dataset_Type
Length:560 Length:560 Length:560 Length:560
Class :character Class :character Class :character Class :character
Mode :character Mode :character Mode :character Mode :character
Accuracy Precision Recall F1_Score
Min. :0.5038 Min. :0.4019 Min. :0.3001 Min. :0.4000
1st Qu.:0.6236 1st Qu.:0.5632 1st Qu.:0.4819 1st Qu.:0.5515
Median :0.7578 Median :0.7195 Median :0.6493 Median :0.7086
Mean :0.8779 Mean :0.8129 Mean :0.7486 Mean :0.8122
3rd Qu.:0.8824 3rd Qu.:0.8596 3rd Qu.:0.8404 3rd Qu.:0.8438
Max. :9.7181 Max. :9.7320 Max. :9.3662 Max. :9.3740
NA's :39 NA's :19 NA's :20 NA's :20
Training_Time Date
Min. : 0.1032 Min. :2023-03-08 11:26:21.07
1st Qu.: 1.2441 1st Qu.:2023-07-26 05:26:21.07
Median : 2.4347 Median :2023-12-12 23:26:21.07
Mean : 2.9910 Mean :2023-12-12 23:26:21.07
3rd Qu.: 3.8131 3rd Qu.:2024-04-30 17:26:21.07
Max. :46.9856 Max. :2024-09-17 11:26:21.07
NA's :20 Al estar todo correcto, no es necesario realizar ninguna conversión.
A continuación, se dará inicio a la revisión de valores faltantes o NA:
library(readr)
probs1 <- problems(dataset)
probs1_adjusted <- probs1
probs1_adjusted$row <- probs1$row - 1
probs1_adjusted# A tibble: 0 × 4
# ℹ 4 variables: row <dbl>, col <int>, expected <chr>, actual <chr>Mediante la combinación de las funciones, colSum() & is.na(), se realiza un conteo de los valores NA en cada columna de la base de datos:
colSums(is.na(dataset)) Algorithm Framework Problem_Type Dataset_Type Accuracy
0 0 0 0 39
Precision Recall F1_Score Training_Time Date
19 20 20 20 0 De lo anterior, es evidente que los datos faltantes en el dataset, se encuentran presentes únicamente en las columnas correspondientes a variables cuantitativas.
Ahora, se contará el número total de datos NA en el dataset:
sum(is.na(dataset))[1] 118Al detectar 118 registros con datos faltantes, es pertinente realizar un tratamiento a todos ellos. Sin embargo, primero se generan varios gráficos para comprender con mayor claridad la situación del dataset. Estos gráficos también servirán posteriormente para realizar comparaciones una vez que los datos hayan sido tratados.
library(VIM)
aggr(dataset, col = c('navyblue','red'), numbers = TRUE, sortVars = TRUE, labels = names(dataset), cex.axis = .7, gap = 3, ylab = c("Proportion of Missingness","Missingness Pattern"))
Variables sorted by number of missings:
Variable Count
Accuracy 0.06964286
Recall 0.03571429
F1_Score 0.03571429
Training_Time 0.03571429
Precision 0.03392857
Algorithm 0.00000000
Framework 0.00000000
Problem_Type 0.00000000
Dataset_Type 0.00000000
Date 0.00000000Con el mismo propósito, se generará un Missingness Map:
library(Amelia)
missmap(dataset, col = c("red", "blue"), legend = TRUE)
Gracias a este gráfico, se puede afirmar que sólo el 2% de los datos contienen valores NA.
Para dar inicio al tratamiento, se utiliza la función na.omit() para eliminar todas las filas con valores NA en el dataset:
dataset_limpio <- na.omit(dataset)Se generan dos gráficos, uno con los datos originales y otro con los datos eliminados para la variable Accuracy:
library(ggplot2)
ggplot(dataset, aes(x = Accuracy)) +
geom_histogram(fill = "red", color = "black", bins = 30) +
ggtitle("Original Data") +
xlab("Accuracy") +
ylab("Frequency") +
theme_minimal()
ggplot(dataset_limpio, aes(x = Accuracy)) +
geom_histogram(fill = "green", color = "black", bins = 30) +
ggtitle("Listwise Deletion") +
xlab("Accuracy") +
ylab("Frequency") +
theme_minimal()
Se generan dos gráficos, uno con los datos originales y otro con los datos eliminados para la variable Precision:
library(ggplot2)
ggplot(dataset, aes(x = Precision)) +
geom_histogram(fill = "red", color = "black", bins = 30) +
ggtitle("Original Data") +
xlab("Precision") +
ylab("Frequency") +
theme_minimal()
ggplot(dataset_limpio, aes(x = Precision)) +
geom_histogram(fill = "green", color = "black", bins = 30) +
ggtitle("Listwise Deletion") +
xlab("Precision") +
ylab("Frequency") +
theme_minimal()
Se generan dos gráficos, uno con los datos originales y otro con los datos eliminados para la variable Recall:
library(ggplot2)
ggplot(dataset, aes(x = Recall)) +
geom_histogram(fill = "red", color = "black", bins = 30) +
ggtitle("Original Data") +
xlab("Recall") +
ylab("Frequency") +
theme_minimal()
ggplot(dataset_limpio, aes(x = Recall)) +
geom_histogram(fill = "green", color = "black", bins = 30) +
ggtitle("Listwise Deletion") +
xlab("Recall") +
ylab("Frequency") +
theme_minimal()
Se generan dos gráficos, uno con los datos originales y otro con los datos eliminados para la variable F1_Score:
library(ggplot2)
ggplot(dataset, aes(x = F1_Score)) +
geom_histogram(fill = "red", color = "black", bins = 30) +
ggtitle("Original Data") +
xlab("F1_Score") +
ylab("Frequency") +
theme_minimal()
ggplot(dataset_limpio, aes(x = F1_Score)) +
geom_histogram(fill = "green", color = "black", bins = 30) +
ggtitle("Listwise Deletion") +
xlab("F1_Score") +
ylab("Frequency") +
theme_minimal()
Se generan dos gráficos, uno con los datos originales y otro con los datos eliminagos para la variable Training_Time:
library(ggplot2)
ggplot(dataset, aes(x = Training_Time)) +
geom_histogram(fill = "red", color = "black", bins = 30) +
ggtitle("Original Data") +
xlab("Training_Time") +
ylab("Frequency") +
theme_minimal()
ggplot(dataset_limpio, aes(x = Training_Time)) +
geom_histogram(fill = "green", color = "black", bins = 30) +
ggtitle("Listwise Deletion") +
xlab("Training_Time") +
ylab("Frequency") +
theme_minimal()
Todos estos gráficos, demustran que la distribución de cada variable se mantiene igual, aún tras haber eliminados los datos faltantes.
Por supuesto, se genera un nuevo Missingness Map, con los datos NA eliminados:
library(Amelia)
missmap(dataset_limpio, col = c("red", "blue"), legend = TRUE)
Como se puede observer, se obtuvo un 0% de datos faltantes, por lo tanto, se puede afirmar que el tratamiento fue exitoso.
En el siguiente paso, se realizará el resumen estadístico inicial, utilizando por supuesto, el dataset limpio.
Se utiliza la función summary para mostrar las medidas de tendencia central y dispersión para cada variable:
summary(dataset_limpio) Algorithm Framework Problem_Type Dataset_Type
Length:448 Length:448 Length:448 Length:448
Class :character Class :character Class :character Class :character
Mode :character Mode :character Mode :character Mode :character
Accuracy Precision Recall F1_Score
Min. :0.5038 Min. :0.4031 Min. :0.3001 Min. :0.4000
1st Qu.:0.6183 1st Qu.:0.5661 1st Qu.:0.4898 1st Qu.:0.5486
Median :0.7490 Median :0.7275 Median :0.6513 Median :0.7031
Mean :0.8458 Mean :0.8387 Mean :0.7611 Mean :0.8014
3rd Qu.:0.8698 3rd Qu.:0.8670 3rd Qu.:0.8365 3rd Qu.:0.8396
Max. :9.7181 Max. :9.7320 Max. :9.3662 Max. :9.3740
Training_Time Date
Min. : 0.1032 Min. :2023-03-10 11:26:21.07
1st Qu.: 1.2982 1st Qu.:2023-08-02 23:26:21.07
Median : 2.4809 Median :2023-12-24 23:26:21.07
Mean : 3.0598 Mean :2023-12-19 17:35:59.65
3rd Qu.: 3.8446 3rd Qu.:2024-05-07 05:26:21.07
Max. :46.9856 Max. :2024-09-17 11:26:21.07 A su vez, se realiza la detección de outliers, para lo se crearán varios diagramas de caja y bigote que correspondan a cada variable numérica:
boxplot(dataset_limpio$Accuracy, ylab = "Accuracy")
boxplot(dataset_limpio$Precision, ylab = "Precision")
boxplot(dataset_limpio$Recall, ylab = "Recall")
boxplot(dataset_limpio$F1_Score, ylab = "F1_Score")
boxplot(dataset_limpio$Training_Time, ylab = "Training_Time")
Al todas las variables numéricas tener una cantidad significativa de valores atípicos, es necesario aplicar técnicas de limpieza o imputación:
Para ello, se utiliza la librería mice para crear un nuevo dataset con los outliers imputados.
variables_numericas <- c("Accuracy", "Precision", "Recall", "F1_Score", "Training_Time")
for (var in variables_numericas) {
x <- dataset[[var]]
qnt <- quantile(x, probs = c(.25, .75), na.rm = TRUE)
H <- 1.5 * IQR(x, na.rm = TRUE)
#se sacan los valores atípicos
limite_inferior <- qnt[1] - H
limite_superior <- qnt[2] + H
mediana <- median(x, na.rm = TRUE)
#Se realiza la imputación en base a la mediana
x[x < limite_inferior] <- mediana
x[x > limite_superior] <- mediana
dataset[[var]] <- x
}
head(dataset)# A tibble: 6 × 10
Algorithm Framework Problem_Type Dataset_Type Accuracy Precision Recall
<chr> <chr> <chr> <chr> <dbl> <dbl> <dbl>
1 SVM Scikit-lea… Regression Time Series 0.662 0.693 NA
2 K-Means Keras Clustering Time Series 0.744 0.490 0.877
3 Neural Network Keras Clustering Image 0.885 0.595 0.969
4 SVM Keras Clustering Text 0.842 0.842 0.875
5 SVM Scikit-lea… Regression Tabular 0.723 0.686 0.301
6 K-Means PyTorch Regression Image 0.637 0.626 0.649
# ℹ 3 more variables: F1_Score <dbl>, Training_Time <dbl>, Date <dttm>library(mice)
imputacion <- mice(dataset[, c("Accuracy", "Precision", "Recall", "F1_Score", "Training_Time")], method = "pmm", m = 5, maxit = 50, seed = 500)
iter imp variable
1 1 Accuracy Precision Recall F1_Score Training_Time
1 2 Accuracy Precision Recall F1_Score Training_Time
1 3 Accuracy Precision Recall F1_Score Training_Time
1 4 Accuracy Precision Recall F1_Score Training_Time
1 5 Accuracy Precision Recall F1_Score Training_Time
2 1 Accuracy Precision Recall F1_Score Training_Time
2 2 Accuracy Precision Recall F1_Score Training_Time
2 3 Accuracy Precision Recall F1_Score Training_Time
2 4 Accuracy Precision Recall F1_Score Training_Time
2 5 Accuracy Precision Recall F1_Score Training_Time
3 1 Accuracy Precision Recall F1_Score Training_Time
3 2 Accuracy Precision Recall F1_Score Training_Time
3 3 Accuracy Precision Recall F1_Score Training_Time
3 4 Accuracy Precision Recall F1_Score Training_Time
3 5 Accuracy Precision Recall F1_Score Training_Time
4 1 Accuracy Precision Recall F1_Score Training_Time
4 2 Accuracy Precision Recall F1_Score Training_Time
4 3 Accuracy Precision Recall F1_Score Training_Time
4 4 Accuracy Precision Recall F1_Score Training_Time
4 5 Accuracy Precision Recall F1_Score Training_Time
5 1 Accuracy Precision Recall F1_Score Training_Time
5 2 Accuracy Precision Recall F1_Score Training_Time
5 3 Accuracy Precision Recall F1_Score Training_Time
5 4 Accuracy Precision Recall F1_Score Training_Time
5 5 Accuracy Precision Recall F1_Score Training_Time
6 1 Accuracy Precision Recall F1_Score Training_Time
6 2 Accuracy Precision Recall F1_Score Training_Time
6 3 Accuracy Precision Recall F1_Score Training_Time
6 4 Accuracy Precision Recall F1_Score Training_Time
6 5 Accuracy Precision Recall F1_Score Training_Time
7 1 Accuracy Precision Recall F1_Score Training_Time
7 2 Accuracy Precision Recall F1_Score Training_Time
7 3 Accuracy Precision Recall F1_Score Training_Time
7 4 Accuracy Precision Recall F1_Score Training_Time
7 5 Accuracy Precision Recall F1_Score Training_Time
8 1 Accuracy Precision Recall F1_Score Training_Time
8 2 Accuracy Precision Recall F1_Score Training_Time
8 3 Accuracy Precision Recall F1_Score Training_Time
8 4 Accuracy Precision Recall F1_Score Training_Time
8 5 Accuracy Precision Recall F1_Score Training_Time
9 1 Accuracy Precision Recall F1_Score Training_Time
9 2 Accuracy Precision Recall F1_Score Training_Time
9 3 Accuracy Precision Recall F1_Score Training_Time
9 4 Accuracy Precision Recall F1_Score Training_Time
9 5 Accuracy Precision Recall F1_Score Training_Time
10 1 Accuracy Precision Recall F1_Score Training_Time
10 2 Accuracy Precision Recall F1_Score Training_Time
10 3 Accuracy Precision Recall F1_Score Training_Time
10 4 Accuracy Precision Recall F1_Score Training_Time
10 5 Accuracy Precision Recall F1_Score Training_Time
11 1 Accuracy Precision Recall F1_Score Training_Time
11 2 Accuracy Precision Recall F1_Score Training_Time
11 3 Accuracy Precision Recall F1_Score Training_Time
11 4 Accuracy Precision Recall F1_Score Training_Time
11 5 Accuracy Precision Recall F1_Score Training_Time
12 1 Accuracy Precision Recall F1_Score Training_Time
12 2 Accuracy Precision Recall F1_Score Training_Time
12 3 Accuracy Precision Recall F1_Score Training_Time
12 4 Accuracy Precision Recall F1_Score Training_Time
12 5 Accuracy Precision Recall F1_Score Training_Time
13 1 Accuracy Precision Recall F1_Score Training_Time
13 2 Accuracy Precision Recall F1_Score Training_Time
13 3 Accuracy Precision Recall F1_Score Training_Time
13 4 Accuracy Precision Recall F1_Score Training_Time
13 5 Accuracy Precision Recall F1_Score Training_Time
14 1 Accuracy Precision Recall F1_Score Training_Time
14 2 Accuracy Precision Recall F1_Score Training_Time
14 3 Accuracy Precision Recall F1_Score Training_Time
14 4 Accuracy Precision Recall F1_Score Training_Time
14 5 Accuracy Precision Recall F1_Score Training_Time
15 1 Accuracy Precision Recall F1_Score Training_Time
15 2 Accuracy Precision Recall F1_Score Training_Time
15 3 Accuracy Precision Recall F1_Score Training_Time
15 4 Accuracy Precision Recall F1_Score Training_Time
15 5 Accuracy Precision Recall F1_Score Training_Time
16 1 Accuracy Precision Recall F1_Score Training_Time
16 2 Accuracy Precision Recall F1_Score Training_Time
16 3 Accuracy Precision Recall F1_Score Training_Time
16 4 Accuracy Precision Recall F1_Score Training_Time
16 5 Accuracy Precision Recall F1_Score Training_Time
17 1 Accuracy Precision Recall F1_Score Training_Time
17 2 Accuracy Precision Recall F1_Score Training_Time
17 3 Accuracy Precision Recall F1_Score Training_Time
17 4 Accuracy Precision Recall F1_Score Training_Time
17 5 Accuracy Precision Recall F1_Score Training_Time
18 1 Accuracy Precision Recall F1_Score Training_Time
18 2 Accuracy Precision Recall F1_Score Training_Time
18 3 Accuracy Precision Recall F1_Score Training_Time
18 4 Accuracy Precision Recall F1_Score Training_Time
18 5 Accuracy Precision Recall F1_Score Training_Time
19 1 Accuracy Precision Recall F1_Score Training_Time
19 2 Accuracy Precision Recall F1_Score Training_Time
19 3 Accuracy Precision Recall F1_Score Training_Time
19 4 Accuracy Precision Recall F1_Score Training_Time
19 5 Accuracy Precision Recall F1_Score Training_Time
20 1 Accuracy Precision Recall F1_Score Training_Time
20 2 Accuracy Precision Recall F1_Score Training_Time
20 3 Accuracy Precision Recall F1_Score Training_Time
20 4 Accuracy Precision Recall F1_Score Training_Time
20 5 Accuracy Precision Recall F1_Score Training_Time
21 1 Accuracy Precision Recall F1_Score Training_Time
21 2 Accuracy Precision Recall F1_Score Training_Time
21 3 Accuracy Precision Recall F1_Score Training_Time
21 4 Accuracy Precision Recall F1_Score Training_Time
21 5 Accuracy Precision Recall F1_Score Training_Time
22 1 Accuracy Precision Recall F1_Score Training_Time
22 2 Accuracy Precision Recall F1_Score Training_Time
22 3 Accuracy Precision Recall F1_Score Training_Time
22 4 Accuracy Precision Recall F1_Score Training_Time
22 5 Accuracy Precision Recall F1_Score Training_Time
23 1 Accuracy Precision Recall F1_Score Training_Time
23 2 Accuracy Precision Recall F1_Score Training_Time
23 3 Accuracy Precision Recall F1_Score Training_Time
23 4 Accuracy Precision Recall F1_Score Training_Time
23 5 Accuracy Precision Recall F1_Score Training_Time
24 1 Accuracy Precision Recall F1_Score Training_Time
24 2 Accuracy Precision Recall F1_Score Training_Time
24 3 Accuracy Precision Recall F1_Score Training_Time
24 4 Accuracy Precision Recall F1_Score Training_Time
24 5 Accuracy Precision Recall F1_Score Training_Time
25 1 Accuracy Precision Recall F1_Score Training_Time
25 2 Accuracy Precision Recall F1_Score Training_Time
25 3 Accuracy Precision Recall F1_Score Training_Time
25 4 Accuracy Precision Recall F1_Score Training_Time
25 5 Accuracy Precision Recall F1_Score Training_Time
26 1 Accuracy Precision Recall F1_Score Training_Time
26 2 Accuracy Precision Recall F1_Score Training_Time
26 3 Accuracy Precision Recall F1_Score Training_Time
26 4 Accuracy Precision Recall F1_Score Training_Time
26 5 Accuracy Precision Recall F1_Score Training_Time
27 1 Accuracy Precision Recall F1_Score Training_Time
27 2 Accuracy Precision Recall F1_Score Training_Time
27 3 Accuracy Precision Recall F1_Score Training_Time
27 4 Accuracy Precision Recall F1_Score Training_Time
27 5 Accuracy Precision Recall F1_Score Training_Time
28 1 Accuracy Precision Recall F1_Score Training_Time
28 2 Accuracy Precision Recall F1_Score Training_Time
28 3 Accuracy Precision Recall F1_Score Training_Time
28 4 Accuracy Precision Recall F1_Score Training_Time
28 5 Accuracy Precision Recall F1_Score Training_Time
29 1 Accuracy Precision Recall F1_Score Training_Time
29 2 Accuracy Precision Recall F1_Score Training_Time
29 3 Accuracy Precision Recall F1_Score Training_Time
29 4 Accuracy Precision Recall F1_Score Training_Time
29 5 Accuracy Precision Recall F1_Score Training_Time
30 1 Accuracy Precision Recall F1_Score Training_Time
30 2 Accuracy Precision Recall F1_Score Training_Time
30 3 Accuracy Precision Recall F1_Score Training_Time
30 4 Accuracy Precision Recall F1_Score Training_Time
30 5 Accuracy Precision Recall F1_Score Training_Time
31 1 Accuracy Precision Recall F1_Score Training_Time
31 2 Accuracy Precision Recall F1_Score Training_Time
31 3 Accuracy Precision Recall F1_Score Training_Time
31 4 Accuracy Precision Recall F1_Score Training_Time
31 5 Accuracy Precision Recall F1_Score Training_Time
32 1 Accuracy Precision Recall F1_Score Training_Time
32 2 Accuracy Precision Recall F1_Score Training_Time
32 3 Accuracy Precision Recall F1_Score Training_Time
32 4 Accuracy Precision Recall F1_Score Training_Time
32 5 Accuracy Precision Recall F1_Score Training_Time
33 1 Accuracy Precision Recall F1_Score Training_Time
33 2 Accuracy Precision Recall F1_Score Training_Time
33 3 Accuracy Precision Recall F1_Score Training_Time
33 4 Accuracy Precision Recall F1_Score Training_Time
33 5 Accuracy Precision Recall F1_Score Training_Time
34 1 Accuracy Precision Recall F1_Score Training_Time
34 2 Accuracy Precision Recall F1_Score Training_Time
34 3 Accuracy Precision Recall F1_Score Training_Time
34 4 Accuracy Precision Recall F1_Score Training_Time
34 5 Accuracy Precision Recall F1_Score Training_Time
35 1 Accuracy Precision Recall F1_Score Training_Time
35 2 Accuracy Precision Recall F1_Score Training_Time
35 3 Accuracy Precision Recall F1_Score Training_Time
35 4 Accuracy Precision Recall F1_Score Training_Time
35 5 Accuracy Precision Recall F1_Score Training_Time
36 1 Accuracy Precision Recall F1_Score Training_Time
36 2 Accuracy Precision Recall F1_Score Training_Time
36 3 Accuracy Precision Recall F1_Score Training_Time
36 4 Accuracy Precision Recall F1_Score Training_Time
36 5 Accuracy Precision Recall F1_Score Training_Time
37 1 Accuracy Precision Recall F1_Score Training_Time
37 2 Accuracy Precision Recall F1_Score Training_Time
37 3 Accuracy Precision Recall F1_Score Training_Time
37 4 Accuracy Precision Recall F1_Score Training_Time
37 5 Accuracy Precision Recall F1_Score Training_Time
38 1 Accuracy Precision Recall F1_Score Training_Time
38 2 Accuracy Precision Recall F1_Score Training_Time
38 3 Accuracy Precision Recall F1_Score Training_Time
38 4 Accuracy Precision Recall F1_Score Training_Time
38 5 Accuracy Precision Recall F1_Score Training_Time
39 1 Accuracy Precision Recall F1_Score Training_Time
39 2 Accuracy Precision Recall F1_Score Training_Time
39 3 Accuracy Precision Recall F1_Score Training_Time
39 4 Accuracy Precision Recall F1_Score Training_Time
39 5 Accuracy Precision Recall F1_Score Training_Time
40 1 Accuracy Precision Recall F1_Score Training_Time
40 2 Accuracy Precision Recall F1_Score Training_Time
40 3 Accuracy Precision Recall F1_Score Training_Time
40 4 Accuracy Precision Recall F1_Score Training_Time
40 5 Accuracy Precision Recall F1_Score Training_Time
41 1 Accuracy Precision Recall F1_Score Training_Time
41 2 Accuracy Precision Recall F1_Score Training_Time
41 3 Accuracy Precision Recall F1_Score Training_Time
41 4 Accuracy Precision Recall F1_Score Training_Time
41 5 Accuracy Precision Recall F1_Score Training_Time
42 1 Accuracy Precision Recall F1_Score Training_Time
42 2 Accuracy Precision Recall F1_Score Training_Time
42 3 Accuracy Precision Recall F1_Score Training_Time
42 4 Accuracy Precision Recall F1_Score Training_Time
42 5 Accuracy Precision Recall F1_Score Training_Time
43 1 Accuracy Precision Recall F1_Score Training_Time
43 2 Accuracy Precision Recall F1_Score Training_Time
43 3 Accuracy Precision Recall F1_Score Training_Time
43 4 Accuracy Precision Recall F1_Score Training_Time
43 5 Accuracy Precision Recall F1_Score Training_Time
44 1 Accuracy Precision Recall F1_Score Training_Time
44 2 Accuracy Precision Recall F1_Score Training_Time
44 3 Accuracy Precision Recall F1_Score Training_Time
44 4 Accuracy Precision Recall F1_Score Training_Time
44 5 Accuracy Precision Recall F1_Score Training_Time
45 1 Accuracy Precision Recall F1_Score Training_Time
45 2 Accuracy Precision Recall F1_Score Training_Time
45 3 Accuracy Precision Recall F1_Score Training_Time
45 4 Accuracy Precision Recall F1_Score Training_Time
45 5 Accuracy Precision Recall F1_Score Training_Time
46 1 Accuracy Precision Recall F1_Score Training_Time
46 2 Accuracy Precision Recall F1_Score Training_Time
46 3 Accuracy Precision Recall F1_Score Training_Time
46 4 Accuracy Precision Recall F1_Score Training_Time
46 5 Accuracy Precision Recall F1_Score Training_Time
47 1 Accuracy Precision Recall F1_Score Training_Time
47 2 Accuracy Precision Recall F1_Score Training_Time
47 3 Accuracy Precision Recall F1_Score Training_Time
47 4 Accuracy Precision Recall F1_Score Training_Time
47 5 Accuracy Precision Recall F1_Score Training_Time
48 1 Accuracy Precision Recall F1_Score Training_Time
48 2 Accuracy Precision Recall F1_Score Training_Time
48 3 Accuracy Precision Recall F1_Score Training_Time
48 4 Accuracy Precision Recall F1_Score Training_Time
48 5 Accuracy Precision Recall F1_Score Training_Time
49 1 Accuracy Precision Recall F1_Score Training_Time
49 2 Accuracy Precision Recall F1_Score Training_Time
49 3 Accuracy Precision Recall F1_Score Training_Time
49 4 Accuracy Precision Recall F1_Score Training_Time
49 5 Accuracy Precision Recall F1_Score Training_Time
50 1 Accuracy Precision Recall F1_Score Training_Time
50 2 Accuracy Precision Recall F1_Score Training_Time
50 3 Accuracy Precision Recall F1_Score Training_Time
50 4 Accuracy Precision Recall F1_Score Training_Time
50 5 Accuracy Precision Recall F1_Score Training_Timedataset_imputado <- complete(imputacion)
dataset$Accuracy <- dataset_imputado$Accuracy
dataset$Precision <- dataset_imputado$Precision
dataset$Recall <- dataset_imputado$Recall
dataset$F1_Score <- dataset_imputado$F1_Score
dataset$Training_Time <- dataset_imputado$Training_TimeSe generan nuevamente los boxplots correspondientes a las variables numéricas, con el fin de verificar que el tratamiento haya funcionado:
boxplot(dataset$Accuracy, ylab = "Accuracy")
boxplot(dataset$Precision, ylab = "Precision")
boxplot(dataset$Recall, ylab = "Recall")
boxplot(dataset$F1_Score, ylab = "F1_Score")
boxplot(dataset$Training_Time, ylab = "Training_Time")
Como se puede apreciar, ya no se evidencian valores atípicos presentes en los diagramas de caja y bigote, por lo que se puede afirmar que la imputación de outliers funcionó correctamente.
Se analizan las variables categóricas. Para cada una de ellas, se saca su tabla de frecuencia, medidas de tendencia central, medidas de dispersión, curtosis y asimetría. Es importante anotar, que en las variables categóricas, no es posible verificar la distribución normal, pues las pruebas de normalidad, están reservadas para las variables cuantitativas o numéricas. Además, se omiten los diagramas de caja y bigote, pues fueron estudiados anteriormente.
Para Algorithm:
library(e1071)
library(dplyr)
variable <- dataset$Algorithm
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
barplot(frecuencia, main="Distribución de la Variable Algorithm",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
K-Means Neural Network Random Forest SVM
163 135 126 136 print(paste("Media:", media))[1] "Media: 2.41964285714286"print(paste("Mediana:", mediana))[1] "Mediana: 2"print(paste("Moda:", moda))[1] "Moda: K-Means"print(paste("Varianza:", varianza))[1] "Varianza: 1.31374584717608"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 1.14618752705484"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 4"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.41816896675628"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0.100895122891551"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles)25% 50% 75%
1 2 3 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95%
1 1 1 1 1 2 2 2 2 2 3 3 3 3 3 4 4 4 4 Para Framework:
library(e1071)
library(dplyr)
variable <- dataset$Framework
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
barplot(frecuencia, main="Distribución de la Variable Framework",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
Keras PyTorch Scikit-learn TensorFlow
124 135 134 167 print(paste("Media:", media))[1] "Media: 2.61428571428571"print(paste("Mediana:", mediana))[1] "Mediana: 3"print(paste("Moda:", moda))[1] "Moda: TensorFlow"print(paste("Varianza:", varianza))[1] "Varianza: 1.27850753897266"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 1.13071107670026"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 4"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.38315005467743"print(paste("Asimetría:", asimetria))[1] "Asimetría: -0.124601550692842"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles)25% 50% 75%
2 3 4 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95%
1 1 1 1 2 2 2 2 2 3 3 3 3 3 4 4 4 4 4 Para Problem_Type:
library(e1071)
library(dplyr)
variable <- dataset$Problem_Type
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
barplot(frecuencia, main="Distribución de la Variable Problem_Type",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
Classification Clustering Regression
175 196 189 print(paste("Media:", media))[1] "Media: 2.025"print(paste("Mediana:", mediana))[1] "Mediana: 2"print(paste("Moda:", moda))[1] "Moda: Clustering"print(paste("Varianza:", varianza))[1] "Varianza: 0.650536672629696"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 0.806558536393792"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 3"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.46422623496655"print(paste("Asimetría:", asimetria))[1] "Asimetría: -0.0452047551811593"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles)25% 50% 75%
1 2 3 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95%
1 1 1 1 1 1 2 2 2 2 2 2 2 3 3 3 3 3 3 Para Dataset_Type:
library(e1071)
library(dplyr)
variable <- dataset$Dataset_Type
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
barplot(frecuencia, main="Distribución de la Variable Dataset_Type",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
Image Tabular Text Time Series
157 136 143 124 print(paste("Media:", media))[1] "Media: 2.41785714285714"print(paste("Mediana:", mediana))[1] "Mediana: 2"print(paste("Moda:", moda))[1] "Moda: Image"print(paste("Varianza:", varianza))[1] "Varianza: 1.24905443393815"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 1.11761103875103"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 4"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.36090786026508"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0.0791470485338742"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles)25% 50% 75%
1 2 3 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55% 60% 65% 70% 75% 80% 85% 90% 95%
1 1 1 1 1 2 2 2 2 2 3 3 3 3 3 4 4 4 4 Para Date:
library(e1071)
library(dplyr)
variable <- dataset$Date
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
barplot(frecuencia, main="Distribución de la Variable Date",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
2023-03-08 11:26:21.08 2023-03-09 11:26:21.08 2023-03-10 11:26:21.08
1 1 1
2023-03-11 11:26:21.08 2023-03-12 11:26:21.08 2023-03-13 11:26:21.08
1 1 1
2023-03-14 11:26:21.08 2023-03-15 11:26:21.08 2023-03-16 11:26:21.08
1 1 1
2023-03-17 11:26:21.08 2023-03-18 11:26:21.08 2023-03-19 11:26:21.08
1 1 1
2023-03-20 11:26:21.08 2023-03-21 11:26:21.08 2023-03-22 11:26:21.08
1 1 1
2023-03-23 11:26:21.08 2023-03-24 11:26:21.08 2023-03-25 11:26:21.08
1 1 1
2023-03-26 11:26:21.08 2023-03-27 11:26:21.08 2023-03-28 11:26:21.08
1 1 1
2023-03-29 11:26:21.08 2023-03-30 11:26:21.08 2023-03-31 11:26:21.08
1 1 1
2023-04-01 11:26:21.08 2023-04-02 11:26:21.08 2023-04-03 11:26:21.08
1 1 1
2023-04-04 11:26:21.08 2023-04-05 11:26:21.08 2023-04-06 11:26:21.08
1 1 1
2023-04-07 11:26:21.08 2023-04-08 11:26:21.08 2023-04-09 11:26:21.08
1 1 1
2023-04-10 11:26:21.08 2023-04-11 11:26:21.08 2023-04-12 11:26:21.08
1 1 1
2023-04-13 11:26:21.08 2023-04-14 11:26:21.08 2023-04-15 11:26:21.08
1 1 1
2023-04-16 11:26:21.08 2023-04-17 11:26:21.08 2023-04-18 11:26:21.08
1 1 1
2023-04-19 11:26:21.08 2023-04-20 11:26:21.08 2023-04-21 11:26:21.08
1 1 1
2023-04-22 11:26:21.08 2023-04-23 11:26:21.08 2023-04-24 11:26:21.08
1 1 1
2023-04-25 11:26:21.08 2023-04-26 11:26:21.08 2023-04-27 11:26:21.08
1 1 1
2023-04-28 11:26:21.08 2023-04-29 11:26:21.08 2023-04-30 11:26:21.08
1 1 1
2023-05-01 11:26:21.08 2023-05-02 11:26:21.08 2023-05-03 11:26:21.08
1 1 1
2023-05-04 11:26:21.08 2023-05-05 11:26:21.08 2023-05-06 11:26:21.08
1 1 1
2023-05-07 11:26:21.08 2023-05-08 11:26:21.08 2023-05-09 11:26:21.08
1 1 1
2023-05-10 11:26:21.08 2023-05-11 11:26:21.08 2023-05-12 11:26:21.08
1 1 1
2023-05-13 11:26:21.08 2023-05-14 11:26:21.08 2023-05-15 11:26:21.08
1 1 1
2023-05-16 11:26:21.08 2023-05-17 11:26:21.08 2023-05-18 11:26:21.08
1 1 1
2023-05-19 11:26:21.08 2023-05-20 11:26:21.08 2023-05-21 11:26:21.08
1 1 1
2023-05-22 11:26:21.08 2023-05-23 11:26:21.08 2023-05-24 11:26:21.08
1 1 1
2023-05-25 11:26:21.08 2023-05-26 11:26:21.08 2023-05-27 11:26:21.08
1 1 1
2023-05-28 11:26:21.08 2023-05-29 11:26:21.08 2023-05-30 11:26:21.08
1 1 1
2023-05-31 11:26:21.08 2023-06-01 11:26:21.08 2023-06-02 11:26:21.08
1 1 1
2023-06-03 11:26:21.08 2023-06-04 11:26:21.08 2023-06-05 11:26:21.08
1 1 1
2023-06-06 11:26:21.08 2023-06-07 11:26:21.08 2023-06-08 11:26:21.08
1 1 1
2023-06-09 11:26:21.08 2023-06-10 11:26:21.08 2023-06-11 11:26:21.08
1 1 1
2023-06-12 11:26:21.08 2023-06-13 11:26:21.08 2023-06-14 11:26:21.08
1 1 1
2023-06-15 11:26:21.08 2023-06-16 11:26:21.08 2023-06-17 11:26:21.08
1 1 1
2023-06-18 11:26:21.08 2023-06-19 11:26:21.08 2023-06-20 11:26:21.08
1 1 1
2023-06-21 11:26:21.08 2023-06-22 11:26:21.08 2023-06-23 11:26:21.08
1 1 1
2023-06-24 11:26:21.08 2023-06-25 11:26:21.08 2023-06-26 11:26:21.08
1 1 1
2023-06-27 11:26:21.08 2023-06-28 11:26:21.08 2023-06-29 11:26:21.08
1 1 1
2023-06-30 11:26:21.08 2023-07-01 11:26:21.08 2023-07-02 11:26:21.08
1 1 1
2023-07-03 11:26:21.08 2023-07-04 11:26:21.08 2023-07-05 11:26:21.08
1 1 1
2023-07-06 11:26:21.08 2023-07-07 11:26:21.08 2023-07-08 11:26:21.08
1 1 1
2023-07-09 11:26:21.08 2023-07-10 11:26:21.08 2023-07-11 11:26:21.08
1 1 1
2023-07-12 11:26:21.08 2023-07-13 11:26:21.08 2023-07-14 11:26:21.08
1 1 1
2023-07-15 11:26:21.08 2023-07-16 11:26:21.08 2023-07-17 11:26:21.08
1 1 1
2023-07-18 11:26:21.08 2023-07-19 11:26:21.08 2023-07-20 11:26:21.08
1 1 1
2023-07-21 11:26:21.08 2023-07-22 11:26:21.08 2023-07-23 11:26:21.08
1 1 1
2023-07-24 11:26:21.08 2023-07-25 11:26:21.08 2023-07-26 11:26:21.08
1 1 1
2023-07-27 11:26:21.08 2023-07-28 11:26:21.08 2023-07-29 11:26:21.08
1 1 1
2023-07-30 11:26:21.08 2023-07-31 11:26:21.08 2023-08-01 11:26:21.08
1 1 1
2023-08-02 11:26:21.08 2023-08-03 11:26:21.08 2023-08-04 11:26:21.08
1 1 1
2023-08-05 11:26:21.08 2023-08-06 11:26:21.08 2023-08-07 11:26:21.08
1 1 1
2023-08-08 11:26:21.08 2023-08-09 11:26:21.08 2023-08-10 11:26:21.08
1 1 1
2023-08-11 11:26:21.08 2023-08-12 11:26:21.08 2023-08-13 11:26:21.08
1 1 1
2023-08-14 11:26:21.08 2023-08-15 11:26:21.08 2023-08-16 11:26:21.08
1 1 1
2023-08-17 11:26:21.08 2023-08-18 11:26:21.08 2023-08-19 11:26:21.08
1 1 1
2023-08-20 11:26:21.08 2023-08-21 11:26:21.08 2023-08-22 11:26:21.08
1 1 1
2023-08-23 11:26:21.08 2023-08-24 11:26:21.08 2023-08-25 11:26:21.08
1 1 1
2023-08-26 11:26:21.08 2023-08-27 11:26:21.08 2023-08-28 11:26:21.08
1 1 1
2023-08-29 11:26:21.08 2023-08-30 11:26:21.08 2023-08-31 11:26:21.08
1 1 1
2023-09-01 11:26:21.08 2023-09-02 11:26:21.08 2023-09-03 11:26:21.08
1 1 1
2023-09-04 11:26:21.08 2023-09-05 11:26:21.08 2023-09-06 11:26:21.08
1 1 1
2023-09-07 11:26:21.08 2023-09-08 11:26:21.08 2023-09-09 11:26:21.08
1 1 1
2023-09-10 11:26:21.08 2023-09-11 11:26:21.08 2023-09-12 11:26:21.08
1 1 1
2023-09-13 11:26:21.08 2023-09-14 11:26:21.08 2023-09-15 11:26:21.08
1 1 1
2023-09-16 11:26:21.08 2023-09-17 11:26:21.08 2023-09-18 11:26:21.08
1 1 1
2023-09-19 11:26:21.08 2023-09-20 11:26:21.08 2023-09-21 11:26:21.08
1 1 1
2023-09-22 11:26:21.08 2023-09-23 11:26:21.08 2023-09-24 11:26:21.08
1 1 1
2023-09-25 11:26:21.08 2023-09-26 11:26:21.08 2023-09-27 11:26:21.08
1 1 1
2023-09-28 11:26:21.08 2023-09-29 11:26:21.08 2023-09-30 11:26:21.08
1 1 1
2023-10-01 11:26:21.08 2023-10-02 11:26:21.08 2023-10-03 11:26:21.08
1 1 1
2023-10-04 11:26:21.08 2023-10-05 11:26:21.08 2023-10-06 11:26:21.08
1 1 1
2023-10-07 11:26:21.08 2023-10-08 11:26:21.08 2023-10-09 11:26:21.08
1 1 1
2023-10-10 11:26:21.08 2023-10-11 11:26:21.08 2023-10-12 11:26:21.08
1 1 1
2023-10-13 11:26:21.08 2023-10-14 11:26:21.08 2023-10-15 11:26:21.08
1 1 1
2023-10-16 11:26:21.08 2023-10-17 11:26:21.08 2023-10-18 11:26:21.08
1 1 1
2023-10-19 11:26:21.08 2023-10-20 11:26:21.08 2023-10-21 11:26:21.08
1 1 1
2023-10-22 11:26:21.08 2023-10-23 11:26:21.08 2023-10-24 11:26:21.08
1 1 1
2023-10-25 11:26:21.08 2023-10-26 11:26:21.08 2023-10-27 11:26:21.08
1 1 1
2023-10-28 11:26:21.08 2023-10-29 11:26:21.08 2023-10-30 11:26:21.08
1 1 1
2023-10-31 11:26:21.08 2023-11-01 11:26:21.08 2023-11-02 11:26:21.08
1 1 1
2023-11-03 11:26:21.08 2023-11-04 11:26:21.08 2023-11-05 11:26:21.08
1 1 1
2023-11-06 11:26:21.08 2023-11-07 11:26:21.08 2023-11-08 11:26:21.08
1 1 1
2023-11-09 11:26:21.08 2023-11-10 11:26:21.08 2023-11-11 11:26:21.08
1 1 1
2023-11-12 11:26:21.08 2023-11-13 11:26:21.08 2023-11-14 11:26:21.08
1 1 1
2023-11-15 11:26:21.08 2023-11-16 11:26:21.08 2023-11-17 11:26:21.08
1 1 1
2023-11-18 11:26:21.08 2023-11-19 11:26:21.08 2023-11-20 11:26:21.08
1 1 1
2023-11-21 11:26:21.08 2023-11-22 11:26:21.08 2023-11-23 11:26:21.08
1 1 1
2023-11-24 11:26:21.08 2023-11-25 11:26:21.08 2023-11-26 11:26:21.08
1 1 1
2023-11-27 11:26:21.08 2023-11-28 11:26:21.08 2023-11-29 11:26:21.08
1 1 1
2023-11-30 11:26:21.08 2023-12-01 11:26:21.08 2023-12-02 11:26:21.08
1 1 1
2023-12-03 11:26:21.08 2023-12-04 11:26:21.08 2023-12-05 11:26:21.08
1 1 1
2023-12-06 11:26:21.08 2023-12-07 11:26:21.08 2023-12-08 11:26:21.08
1 1 1
2023-12-09 11:26:21.08 2023-12-10 11:26:21.08 2023-12-11 11:26:21.08
1 1 1
2023-12-12 11:26:21.08 2023-12-13 11:26:21.08 2023-12-14 11:26:21.08
1 1 1
2023-12-15 11:26:21.08 2023-12-16 11:26:21.08 2023-12-17 11:26:21.08
1 1 1
2023-12-18 11:26:21.08 2023-12-19 11:26:21.08 2023-12-20 11:26:21.08
1 1 1
2023-12-21 11:26:21.08 2023-12-22 11:26:21.08 2023-12-23 11:26:21.08
1 1 1
2023-12-24 11:26:21.08 2023-12-25 11:26:21.08 2023-12-26 11:26:21.08
1 1 1
2023-12-27 11:26:21.08 2023-12-28 11:26:21.08 2023-12-29 11:26:21.08
1 1 1
2023-12-30 11:26:21.08 2023-12-31 11:26:21.08 2024-01-01 11:26:21.08
1 1 1
2024-01-02 11:26:21.08 2024-01-03 11:26:21.08 2024-01-04 11:26:21.08
1 1 1
2024-01-05 11:26:21.08 2024-01-06 11:26:21.08 2024-01-07 11:26:21.08
1 1 1
2024-01-08 11:26:21.08 2024-01-09 11:26:21.08 2024-01-10 11:26:21.08
1 1 1
2024-01-11 11:26:21.08 2024-01-12 11:26:21.08 2024-01-13 11:26:21.08
1 1 1
2024-01-14 11:26:21.08 2024-01-15 11:26:21.08 2024-01-16 11:26:21.08
1 1 1
2024-01-17 11:26:21.08 2024-01-18 11:26:21.08 2024-01-19 11:26:21.08
1 1 1
2024-01-20 11:26:21.08 2024-01-21 11:26:21.08 2024-01-22 11:26:21.08
1 1 1
2024-01-23 11:26:21.08 2024-01-24 11:26:21.08 2024-01-25 11:26:21.08
1 1 1
2024-01-26 11:26:21.08 2024-01-27 11:26:21.08 2024-01-28 11:26:21.08
1 1 1
2024-01-29 11:26:21.08 2024-01-30 11:26:21.08 2024-01-31 11:26:21.08
1 1 1
2024-02-01 11:26:21.08 2024-02-02 11:26:21.08 2024-02-03 11:26:21.08
1 1 1
2024-02-04 11:26:21.08 2024-02-05 11:26:21.08 2024-02-06 11:26:21.08
1 1 1
2024-02-07 11:26:21.08 2024-02-08 11:26:21.08 2024-02-09 11:26:21.08
1 1 1
2024-02-10 11:26:21.08 2024-02-11 11:26:21.08 2024-02-12 11:26:21.08
1 1 1
2024-02-13 11:26:21.08 2024-02-14 11:26:21.08 2024-02-15 11:26:21.08
1 1 1
2024-02-16 11:26:21.08 2024-02-17 11:26:21.08 2024-02-18 11:26:21.08
1 1 1
2024-02-19 11:26:21.08 2024-02-20 11:26:21.08 2024-02-21 11:26:21.08
1 1 1
2024-02-22 11:26:21.08 2024-02-23 11:26:21.08 2024-02-24 11:26:21.08
1 1 1
2024-02-25 11:26:21.08 2024-02-26 11:26:21.08 2024-02-27 11:26:21.08
1 1 1
2024-02-28 11:26:21.08 2024-02-29 11:26:21.08 2024-03-01 11:26:21.08
1 1 1
2024-03-02 11:26:21.08 2024-03-03 11:26:21.08 2024-03-04 11:26:21.08
1 1 1
2024-03-05 11:26:21.08 2024-03-06 11:26:21.08 2024-03-07 11:26:21.08
1 1 1
2024-03-08 11:26:21.08 2024-03-09 11:26:21.08 2024-03-10 11:26:21.08
1 1 1
2024-03-11 11:26:21.08 2024-03-12 11:26:21.08 2024-03-13 11:26:21.08
1 1 1
2024-03-14 11:26:21.08 2024-03-15 11:26:21.08 2024-03-16 11:26:21.08
1 1 1
2024-03-17 11:26:21.08 2024-03-18 11:26:21.08 2024-03-19 11:26:21.08
1 1 1
2024-03-20 11:26:21.08 2024-03-21 11:26:21.08 2024-03-22 11:26:21.08
1 1 1
2024-03-23 11:26:21.08 2024-03-24 11:26:21.08 2024-03-25 11:26:21.08
1 1 1
2024-03-26 11:26:21.08 2024-03-27 11:26:21.08 2024-03-28 11:26:21.08
1 1 1
2024-03-29 11:26:21.08 2024-03-30 11:26:21.08 2024-03-31 11:26:21.08
1 1 1
2024-04-01 11:26:21.08 2024-04-02 11:26:21.08 2024-04-03 11:26:21.08
1 1 1
2024-04-04 11:26:21.08 2024-04-05 11:26:21.08 2024-04-06 11:26:21.08
1 1 1
2024-04-07 11:26:21.08 2024-04-08 11:26:21.08 2024-04-09 11:26:21.08
1 1 1
2024-04-10 11:26:21.08 2024-04-11 11:26:21.08 2024-04-12 11:26:21.08
1 1 1
2024-04-13 11:26:21.08 2024-04-14 11:26:21.08 2024-04-15 11:26:21.08
1 1 1
2024-04-16 11:26:21.08 2024-04-17 11:26:21.08 2024-04-18 11:26:21.08
1 1 1
2024-04-19 11:26:21.08 2024-04-20 11:26:21.08 2024-04-21 11:26:21.08
1 1 1
2024-04-22 11:26:21.08 2024-04-23 11:26:21.08 2024-04-24 11:26:21.08
1 1 1
2024-04-25 11:26:21.08 2024-04-26 11:26:21.08 2024-04-27 11:26:21.08
1 1 1
2024-04-28 11:26:21.08 2024-04-29 11:26:21.08 2024-04-30 11:26:21.08
1 1 1
2024-05-01 11:26:21.08 2024-05-02 11:26:21.08 2024-05-03 11:26:21.08
1 1 1
2024-05-04 11:26:21.08 2024-05-05 11:26:21.08 2024-05-06 11:26:21.08
1 1 1
2024-05-07 11:26:21.08 2024-05-08 11:26:21.08 2024-05-09 11:26:21.08
1 1 1
2024-05-10 11:26:21.08 2024-05-11 11:26:21.08 2024-05-12 11:26:21.08
1 1 1
2024-05-13 11:26:21.08 2024-05-14 11:26:21.08 2024-05-15 11:26:21.08
1 1 1
2024-05-16 11:26:21.08 2024-05-17 11:26:21.08 2024-05-18 11:26:21.08
1 1 1
2024-05-19 11:26:21.08 2024-05-20 11:26:21.08 2024-05-21 11:26:21.08
1 1 1
2024-05-22 11:26:21.08 2024-05-23 11:26:21.08 2024-05-24 11:26:21.08
1 1 1
2024-05-25 11:26:21.08 2024-05-26 11:26:21.08 2024-05-27 11:26:21.08
1 1 1
2024-05-28 11:26:21.08 2024-05-29 11:26:21.08 2024-05-30 11:26:21.08
1 1 1
2024-05-31 11:26:21.08 2024-06-01 11:26:21.08 2024-06-02 11:26:21.08
1 1 1
2024-06-03 11:26:21.08 2024-06-04 11:26:21.08 2024-06-05 11:26:21.08
1 1 1
2024-06-06 11:26:21.08 2024-06-07 11:26:21.08 2024-06-08 11:26:21.08
1 1 1
2024-06-09 11:26:21.08 2024-06-10 11:26:21.08 2024-06-11 11:26:21.08
1 1 1
2024-06-12 11:26:21.08 2024-06-13 11:26:21.08 2024-06-14 11:26:21.08
1 1 1
2024-06-15 11:26:21.08 2024-06-16 11:26:21.08 2024-06-17 11:26:21.08
1 1 1
2024-06-18 11:26:21.08 2024-06-19 11:26:21.08 2024-06-20 11:26:21.08
1 1 1
2024-06-21 11:26:21.08 2024-06-22 11:26:21.08 2024-06-23 11:26:21.08
1 1 1
2024-06-24 11:26:21.08 2024-06-25 11:26:21.08 2024-06-26 11:26:21.08
1 1 1
2024-06-27 11:26:21.08 2024-06-28 11:26:21.08 2024-06-29 11:26:21.08
1 1 1
2024-06-30 11:26:21.08 2024-07-01 11:26:21.08 2024-07-02 11:26:21.08
1 1 1
2024-07-03 11:26:21.08 2024-07-04 11:26:21.08 2024-07-05 11:26:21.08
1 1 1
2024-07-06 11:26:21.08 2024-07-07 11:26:21.08 2024-07-08 11:26:21.08
1 1 1
2024-07-09 11:26:21.08 2024-07-10 11:26:21.08 2024-07-11 11:26:21.08
1 1 1
2024-07-12 11:26:21.08 2024-07-13 11:26:21.08 2024-07-14 11:26:21.08
1 1 1
2024-07-15 11:26:21.08 2024-07-16 11:26:21.08 2024-07-17 11:26:21.08
1 1 1
2024-07-18 11:26:21.08 2024-07-19 11:26:21.08 2024-07-20 11:26:21.08
1 1 1
2024-07-21 11:26:21.08 2024-07-22 11:26:21.08 2024-07-23 11:26:21.08
1 1 1
2024-07-24 11:26:21.08 2024-07-25 11:26:21.08 2024-07-26 11:26:21.08
1 1 1
2024-07-27 11:26:21.08 2024-07-28 11:26:21.08 2024-07-29 11:26:21.08
1 1 1
2024-07-30 11:26:21.08 2024-07-31 11:26:21.08 2024-08-01 11:26:21.08
1 1 1
2024-08-02 11:26:21.08 2024-08-03 11:26:21.08 2024-08-04 11:26:21.08
1 1 1
2024-08-05 11:26:21.08 2024-08-06 11:26:21.08 2024-08-07 11:26:21.08
1 1 1
2024-08-08 11:26:21.08 2024-08-09 11:26:21.08 2024-08-10 11:26:21.08
1 1 1
2024-08-11 11:26:21.08 2024-08-12 11:26:21.08 2024-08-13 11:26:21.08
1 1 1
2024-08-14 11:26:21.08 2024-08-15 11:26:21.08 2024-08-16 11:26:21.08
1 1 1
2024-08-17 11:26:21.08 2024-08-18 11:26:21.08 2024-08-19 11:26:21.08
1 1 1
2024-08-20 11:26:21.08 2024-08-21 11:26:21.08 2024-08-22 11:26:21.08
1 1 1
2024-08-23 11:26:21.08 2024-08-24 11:26:21.08 2024-08-25 11:26:21.08
1 1 1
2024-08-26 11:26:21.08 2024-08-27 11:26:21.08 2024-08-28 11:26:21.08
1 1 1
2024-08-29 11:26:21.08 2024-08-30 11:26:21.08 2024-08-31 11:26:21.08
1 1 1
2024-09-01 11:26:21.08 2024-09-02 11:26:21.08 2024-09-03 11:26:21.08
1 1 1
2024-09-04 11:26:21.08 2024-09-05 11:26:21.08 2024-09-06 11:26:21.08
1 1 1
2024-09-07 11:26:21.08 2024-09-08 11:26:21.08 2024-09-09 11:26:21.08
1 1 1
2024-09-10 11:26:21.08 2024-09-11 11:26:21.08 2024-09-12 11:26:21.08
1 1 1
2024-09-13 11:26:21.08 2024-09-14 11:26:21.08 2024-09-15 11:26:21.08
1 1 1
2024-09-16 11:26:21.08 2024-09-17 11:26:21.08
1 1 print(paste("Media:", media))[1] "Media: 280.5"print(paste("Mediana:", mediana))[1] "Mediana: 280.5"print(paste("Moda:", moda))[1] "Moda: 2023-03-08 11:26:21.08"print(paste("Varianza:", varianza))[1] "Varianza: 26180"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 161.802348561447"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 560"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.20643045741024"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles) 25% 50% 75%
140.75 280.50 420.25 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55%
28.95 56.90 84.85 112.80 140.75 168.70 196.65 224.60 252.55 280.50 308.45
60% 65% 70% 75% 80% 85% 90% 95%
336.40 364.35 392.30 420.25 448.20 476.15 504.10 532.05 Ahora, se analizan las variables numéricas. En este caso, también se omiten los diagramas de caja y bigote.
Para Accuracy:
library(e1071)
library(dplyr)
variable <- dataset$Accuracy
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
hist(frecuencia, main="Distribución de la Variable Accuracy",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
0.503781437489071 0.504885423709592 0.505515632214324 0.50581026995405
1 1 1 1
0.509116291338181 0.509596138411528 0.511819293023168 0.512821032903218
1 1 1 1
0.512905953474744 0.514986794936339 0.515193529848418 0.515326251102903
1 1 1 1
0.515567041442256 0.515793072412821 0.516601554395683 0.518080190262381
1 1 1 1
0.518335713466771 0.519671770334255 0.519809412674179 0.520786429525196
1 1 1 1
0.52170626642741 0.524106019430278 0.528543428044657 0.528890280498183
1 1 2 1
0.529081897752738 0.530071171300393 0.53013369514478 0.530176041995282
3 4 1 1
0.530674813555334 0.531145899065031 0.532104468537567 0.533806281796107
1 1 1 1
0.534086154692747 0.534711921373047 0.536099204489588 0.536223443897279
1 1 2 1
0.536597961884222 0.53928924857751 0.539709684494493 0.540057423192338
2 1 1 1
0.540459641525626 0.541190522807921 0.542829124798215 0.543821373381919
1 1 1 1
0.543933249572417 0.544562216058008 0.547767656917334 0.547857277760081
1 1 1 1
0.54833822482336 0.549041290392122 0.550522905505323 0.550710414224608
1 1 1 1
0.552054824692083 0.5522839201672 0.552465089209087 0.552832342130872
1 1 1 1
0.553296515153995 0.554868099338752 0.555959809698864 0.558183198942738
1 1 1 1
0.558654094481197 0.560104527685304 0.560692469711214 0.560943046668474
1 1 1 2
0.561054957005013 0.562592896101275 0.563856741817617 0.564197144727063
1 1 1 1
0.5653551883701 0.565436830359175 0.565622438841194 0.566262336370924
1 2 1 1
0.56635787702153 0.567583144577411 0.568219876278367 0.568554852864499
1 1 1 1
0.569825627378156 0.571124684343598 0.571247771450757 0.573186996081125
1 1 1 1
0.57552894589045 0.576012426564324 0.576208006665209 0.579772340056594
1 2 1 1
0.581761936292511 0.581811910595835 0.583520953950475 0.583741291129535
3 1 1 1
0.583809608144159 0.584007103872432 0.58487895254377 0.586762257493254
1 3 1 1
0.587419313630206 0.58765147117883 0.588574894723693 0.589841554435121
1 1 1 1
0.590488476354745 0.59057467476734 0.590719173847813 0.59105895784435
1 1 1 1
0.595933662359371 0.597311255910383 0.599771225464573 0.600075122122405
1 1 1 1
0.600262363350168 0.600466844329528 0.600926726061474 0.602920605018384
2 1 1 1
0.604255257178668 0.606022419954113 0.607600936008619 0.607837576198859
1 1 1 2
0.6080190912548 0.608369900045388 0.609606993679022 0.61038480639438
1 1 1 1
0.613328201113494 0.613634813631576 0.614039885974466 0.614977302945543
1 1 1 1
0.615973548057988 0.616856040955217 0.617321040927727 0.618025231673232
1 1 1 1
0.618435279487241 0.618771662461939 0.619590052107963 0.620600728799771
1 1 1 1
0.621022507931264 0.623551617005073 0.623615537201589 0.624357136293815
1 1 1 1
0.628281391850682 0.628388283860254 0.629906604372517 0.631556284955421
1 1 1 1
0.634496702217549 0.634874805758495 0.636312000366767 0.636629763499105
1 1 1 1
0.636813333140833 0.637080333279903 0.637107601174335 0.637403017774068
2 1 1 1
0.638413898617526 0.642436450980961 0.645831289354652 0.651564177972664
1 1 1 1
0.651637573783798 0.65233956954902 0.652762155329012 0.653126810393306
1 1 1 1
0.653644982463143 0.653964970795595 0.655180979461787 0.655653849578002
1 1 1 1
0.65590806654263 0.658078052488375 0.66168578105776 0.661805109574771
1 1 1 1
0.662166876557688 0.662292914950135 0.662595032112347 0.663230654121996
1 1 1 1
0.663516580781619 0.666500956529099 0.668447895885553 0.668501588215643
1 1 1 1
0.669725096271403 0.670623913813078 0.673049863268893 0.673785762119491
1 1 1 1
0.67531346560459 0.675811343619817 0.676710689651359 0.677498152915969
1 1 1 1
0.679616684699883 0.680068203735759 0.683230767435699 0.683767211145766
1 1 2 1
0.683879675438645 0.684263171861881 0.685519381492301 0.68662589581467
1 1 1 1
0.689892890089615 0.69031164673829 0.694279050635173 0.695452997952757
1 1 2 1
0.69554076832588 0.696246778203342 0.696932202827079 0.698086345804628
1 1 1 1
0.698461638100798 0.698490758537142 0.698797198981397 0.699331513886157
1 1 1 1
0.69941139044845 0.699657957904654 0.701490089382581 0.702070160825516
1 1 1 1
0.702159384052146 0.703453980361435 0.704667003157522 0.705514234903352
1 1 1 1
0.706774550762676 0.707064876264464 0.708076999089881 0.709863658463061
1 1 1 1
0.710860463436728 0.711869126824381 0.713041691945186 0.713090651117986
1 1 1 1
0.714099807462807 0.715152947449731 0.716167400521301 0.716248939165066
1 1 1 1
0.717791657406466 0.719307709594795 0.719755844316455 0.721875109652286
1 1 1 1
0.722652627501333 0.722951353188374 0.723601270252418 0.724346811311265
1 1 1 1
0.726099514141718 0.72615914225915 0.72718866727998 0.72736992781693
1 1 2 1
0.727610074540901 0.72990021188466 0.731311478369658 0.731747021900286
1 1 1 1
0.732602806141859 0.736604953345779 0.737315437874907 0.739590938814865
1 1 1 1
0.739969417358562 0.740253473628914 0.740672075817662 0.740761175756275
1 1 1 1
0.741772823359962 0.742935879593163 0.743334470712351 0.743530959409468
1 1 1 1
0.743927021963181 0.744321595202333 0.74442329012846 0.745797273370718
1 1 1 1
0.746138928224017 0.748383429429585 0.748481741452915 0.748587382004214
1 1 1 1
0.749097858226569 0.749444076725678 0.751283038231721 0.753070931420122
1 1 1 1
0.753617404344196 0.754711064074895 0.757408676964845 0.757798014289625
1 1 1 2
0.757839713848249 0.758855821692356 0.759529895454135 0.759540892568109
11 1 1 1
0.759886974278009 0.760478988636021 0.76258169183353 0.763201330468057
1 1 1 1
0.763520731955826 0.765584764000516 0.766478893275668 0.766801273363439
1 1 1 1
0.767655065726296 0.767913842236541 0.769580638337627 0.76997856514028
1 1 1 1
0.770005957302255 0.770648167650535 0.772244548980425 0.773348706357035
1 1 1 1
0.773796188076868 0.773979744486846 0.774764767947508 0.775113271078131
1 1 1 1
0.776901120356188 0.777681775468816 0.778891708685012 0.779824341743457
1 1 1 1
0.781148407938955 0.783508130493334 0.783656109814452 0.783770424130779
1 1 1 1
0.785304873319415 0.789193458503205 0.789337704286197 0.790985700957199
1 1 1 1
0.792677182198376 0.793304231587737 0.796175164296681 0.796475425717464
1 1 1 1
0.797238167593087 0.800010274059652 0.800297166680309 0.800805910073166
1 1 1 1
0.801724296690689 0.803126468875489 0.80354701804439 0.803952546396722
3 1 1 1
0.805166891655459 0.805490494425496 0.807609719115505 0.808325157260369
2 1 1 1
0.808572493302015 0.808923620100607 0.809077867159059 0.809745173004807
1 1 1 1
0.809793977448915 0.811483291781741 0.811929662338287 0.811947918145819
1 1 1 1
0.813110160815708 0.81578011004626 0.816575687797011 0.818215124771818
1 1 1 1
0.819262973832043 0.81955996890775 0.820413157345103 0.820486038672666
1 1 1 1
0.820985750221633 0.821788847598262 0.823737357077301 0.825100546199077
1 1 1 1
0.825162843173468 0.825438684523597 0.825616488520746 0.825833412687943
1 1 1 1
0.828368332270646 0.828922652301518 0.829353887750438 0.831902263810903
1 1 1 1
0.832455862243609 0.833432128773052 0.833774949645735 0.833796692781792
1 1 1 1
0.834106399277508 0.834743477599095 0.836301059112563 0.836716216662459
1 1 1 1
0.838256692888623 0.840114121215646 0.840249651037356 0.841624014144823
1 1 1 1
0.841647688303253 0.842782643614486 0.844732484568633 0.844763375515781
1 1 1 1
0.846080670847066 0.846218075662185 0.846312976113082 0.846841112890744
1 1 1 1
0.847475544451231 0.847490943063271 0.847517614429277 0.851232485272052
1 1 1 1
0.852340381368323 0.853388608442723 0.854372348871488 0.854523130861216
2 1 3 1
0.854530259725458 0.857043466066214 0.858075337111597 0.858798882829088
1 1 1 1
0.859061538113247 0.859600889136132 0.862169408564371 0.862628830207568
1 1 1 2
0.863584534883154 0.865325255119623 0.865794760877666 0.866556511207641
1 1 1 1
0.866807190280701 0.86820100753282 0.868436872472091 0.869224604625663
1 1 1 1
0.871353260599991 0.877635210248404 0.878081664447623 0.880144911561068
1 2 1 1
0.880511995471499 0.881142567388308 0.882404900451498 0.882441630771064
1 4 1 1
0.88465244682067 0.885203708903897 0.885460922322026 0.8867365628433
1 1 1 1
0.888298426395871 0.889925494446675 0.890262757621931 0.89038079303422
1 1 1 1
0.891014043835193 0.891192742029137 0.89484925357124 0.895015218153531
1 1 1 1
0.897404774374965 0.897724980394865 0.898268645488088 0.898779550318594
1 1 1 1
0.898906824429317 0.900178253911181 0.900293349554541 0.900768555941495
1 1 1 1
0.900864041534896 0.901512948916332 0.902835076475027 0.902996274887579
1 1 1 1
0.903922970970629 0.906492869358047 0.906985134753009 0.908648884981247
1 1 1 1
0.908724854245596 0.908917108087511 0.909594429713395 0.911240281817181
1 1 2 1
0.911307159256839 0.913033815126264 0.913768947783437 0.914441682941305
1 1 1 1
0.91993065143336 0.921016647188211 0.922085224484599 0.922178541369808
1 1 1 1
0.922391614058444 0.925712478872548 0.92719254668479 0.930061198594602
1 1 1 1
0.931007241136311 0.931398538771614 0.931666824785913 0.933959147260011
1 1 1 1
0.934028345053725 0.934071127188753 0.934135640256629 0.93413625270419
1 1 1 1
0.934311583977805 0.934452492239359 0.935374950636256 0.93537672516863
1 2 1 1
0.935484561873043 0.935891783296101 0.93671161904083 0.938987160222535
1 1 1 1
0.939257780650674 0.940039543780729 0.942103231674204 0.943302107620233
1 1 1 1
0.947049601839567 0.947095437332059 0.947408328030264 0.950011561699006
1 1 1 1
0.950350932005629 0.954516260332821 0.956181672808345 0.959695986607209
1 1 1 1
0.960423923907843 0.961378595256697 0.963500483962148 0.963517272398153
1 1 1 1
0.963588909739726 0.965297607321958 0.965474347753489 0.966937508763952
3 1 1 1
0.967218013402757 0.968106123121845 0.968302846147481 0.968478911515531
1 1 1 1
0.972307109737012 0.975431781125205 0.975701671103329 0.97590589271162
1 1 1 1
0.977761847977467 0.97881264225269 0.979788322160517 0.98146343761879
1 1 1 1
0.981557555794587 0.982559348218023 0.98291108057661 0.984096713957361
1 1 1 1
0.984706161167644 0.984910522539272 0.984956023053635 0.98569754702082
1 1 1 2
0.987396581073392 0.987805100429958 0.987932627909566 0.987936877455027
1 1 1 1
0.988587092110659 0.991839462631707 0.991988823979914 0.993315061479424
1 1 1 1
0.993331296633573 0.993892760107444 0.995627996851094 0.996079007411656
1 1 1 1
0.996241751079188 0.997069680610584 0.997433158584884 0.998166958028371
1 2 1 1
0.998348426926488 0.998562250078856 0.999706862885333
1 1 1 print(paste("Media:", media))[1] "Media: 253.894642857143"print(paste("Mediana:", mediana))[1] "Mediana: 259.5"print(paste("Moda:", moda))[1] "Moda: 0.757839713848249"print(paste("Varianza:", varianza))[1] "Varianza: 21859.579219908"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 147.849853635058"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 511"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.20613295365698"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0.00583851473392025"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles) 25% 50% 75%
123.75 259.50 381.25 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55%
25.95 48.90 74.85 97.80 123.75 150.70 178.65 204.60 231.55 259.50 276.45
60% 65% 70% 75% 80% 85% 90% 95%
304.40 329.35 357.30 381.25 405.20 432.15 459.10 485.05 De este histograma, se infiere que la distribución de esta variable no es normal, y además, está sesgada hacia la derecha.
Para Precision:
library(e1071)
library(dplyr)
variable <- dataset$Precision
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
hist(frecuencia, main="Distribución de la Variable Precision",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
0.401930958162567 0.403137768125748 0.403303479496253 0.404598419589535
1 1 1 1
0.407442421766389 0.410803933360273 0.412566976618548 0.413094038065294
1 1 1 1
0.415718025119239 0.416300452735336 0.419913612737456 0.42016816010997
1 1 1 1
0.42080216003589 0.421186812964144 0.422032817500493 0.423055809377395
1 1 1 2
0.425003740361431 0.425170734058982 0.425214805102843 0.425904241478207
1 1 2 1
0.42738924730143 0.428885701587012 0.431173946532561 0.431354727571614
1 1 1 1
0.435130557546388 0.437363863529131 0.437591922073213 0.438184545571985
1 1 1 1
0.438912156689781 0.439122754756295 0.439219694538631 0.439991224336414
1 1 1 1
0.440601017140001 0.441374809813853 0.441784688897443 0.442559329680264
1 1 1 1
0.442754036659155 0.443250601599204 0.447381497314497 0.447643950785818
1 1 1 1
0.448360908254275 0.449035207448067 0.449303000485856 0.45007845099363
1 1 1 1
0.450875209627482 0.452255660077463 0.45316025780777 0.455794383893879
1 1 1 1
0.456314370894014 0.457920682117264 0.459037389828038 0.45950685975233
1 1 1 1
0.46038248711412 0.462534881685009 0.463284219973978 0.464815452478415
1 1 1 1
0.466593681528089 0.467548234247162 0.468303036085961 0.46845747093276
1 1 1 1
0.468861323121531 0.46895979823574 0.471001714554032 0.472831850895644
1 1 1 1
0.472900825780551 0.475758844938702 0.47685744781972 0.478893471938789
1 1 1 1
0.479037264072737 0.480087983449566 0.481212449366611 0.483547222670557
1 1 1 1
0.484014458531991 0.484426916829255 0.485183193856596 0.48847151602377
1 1 1 1
0.489332830199467 0.490029198816391 0.490101400490225 0.490748097240961
1 1 1 1
0.491262569933364 0.494772893701209 0.495344900601612 0.496042980972744
1 2 1 1
0.497340043469488 0.498823812059377 0.498888889437662 0.499464724097965
1 1 1 1
0.499572937177471 0.504256955881446 0.504465601200451 0.506457261681824
1 1 1 1
0.510534903542816 0.510685751880184 0.511117340720481 0.511198107717229
1 1 1 1
0.511660850707766 0.512447166458549 0.51281484076925 0.517658627643036
1 1 1 1
0.518482293915962 0.518858579655844 0.520818269281585 0.521209401041494
1 2 1 1
0.521488336099142 0.522259875476613 0.522421380777339 0.523412357317333
1 1 1 1
0.524195547063056 0.528106819786403 0.531441285461115 0.532367171626727
1 1 1 1
0.534769367106311 0.535190157970741 0.536307734214109 0.542460081024884
1 1 1 1
0.543706101945723 0.543924467653567 0.544415627099503 0.545136296955303
1 1 1 1
0.548007318712974 0.5481872794432 0.549727719909704 0.550579996804179
1 2 1 1
0.551344612104017 0.552634948505108 0.552802373227631 0.553918037466549
1 1 1 1
0.555172500932823 0.555578055319464 0.556094674577231 0.556172114539602
1 1 1 1
0.557023410241544 0.559027856995002 0.561892432076929 0.563169835677179
1 1 1 1
0.563842485983687 0.564838915311712 0.566088584674784 0.566142692426685
1 1 1 1
0.567565653072646 0.568409929309585 0.568912719048958 0.56931224481592
1 1 1 1
0.571544073543496 0.572282774850745 0.575330938277139 0.575693222020579
2 1 1 1
0.577266866486452 0.577921348772593 0.57834268462517 0.578529070791292
1 1 2 1
0.579235344153264 0.579951466904191 0.580759156456 0.582367840744434
1 1 1 1
0.58285065723168 0.583186406018039 0.583362529294129 0.588610067910249
1 1 1 1
0.589244137448808 0.590167952674672 0.594805556134036 0.595062409259019
1 1 1 1
0.596158969802847 0.596915652165587 0.598129038922899 0.59880820426183
1 1 1 1
0.600542991217637 0.600706773245159 0.601124828422524 0.602960503596699
1 1 1 1
0.603316389603251 0.607133885681015 0.608405995755306 0.6087648469493
1 1 1 1
0.609703823252091 0.60982193784751 0.611424967965793 0.611950845101239
2 1 1 1
0.613230741211444 0.613295806264814 0.614678959195265 0.617111855923083
1 1 1 1
0.617341264991373 0.620985718304109 0.623300214302508 0.625532971087462
1 1 1 1
0.628240329382246 0.628252004504537 0.629163783791738 0.630299771159826
1 1 1 1
0.630706796586888 0.634915418906698 0.636685767142021 0.636745645358588
1 1 1 1
0.637582283597473 0.638209024742315 0.640896589516773 0.645942933817773
1 1 1 1
0.646612645159327 0.647059324950705 0.647573104509174 0.65065658756506
1 1 1 1
0.651275991444497 0.652748831976443 0.653096907123299 0.653529056987167
1 1 1 1
0.656493812752369 0.657794087643361 0.658256446192594 0.659246129766518
1 1 1 1
0.660411619704325 0.660757576515227 0.662110421569108 0.662561874433235
1 1 1 1
0.663642993816671 0.664119398773294 0.664194051021009 0.666028008627513
1 1 1 1
0.668233326283855 0.669166378572726 0.669843905470324 0.670210587343248
1 1 1 1
0.670743606508593 0.674912132042736 0.674980384917194 0.675543926558175
1 1 1 1
0.675559118303928 0.675668061043592 0.676214962721156 0.676323698364484
1 1 1 1
0.676886478774841 0.676934484651874 0.6783588260874 0.678359492013002
1 1 1 1
0.681260779278704 0.682700739359689 0.682772300438899 0.683496013003908
1 1 1 1
0.68561087762126 0.688583733931674 0.689224634867249 0.689781323251213
1 2 1 1
0.692542716204031 0.692600241172759 0.692944682213067 0.696127948204071
1 1 1 1
0.69652746835018 0.69787669141318 0.698687504820574 0.698953409358072
1 1 1 2
0.703124064145983 0.703511615771097 0.703759635697122 0.705016328149768
1 1 1 1
0.707333152487605 0.707418266527474 0.707501589262199 0.707592851887032
1 1 1 1
0.709943577067587 0.710361433864966 0.710467811053025 0.710847259743289
1 1 1 1
0.711044813167123 0.711631515702362 0.713997778716845 0.71403454682462
1 1 1 1
0.716439773273606 0.718181279949495 0.71945240936513 0.719817320347684
1 1 11 1
0.723221078771629 0.724419085986946 0.724476252991327 0.725342323295109
1 1 1 1
0.726122930405588 0.727016151338163 0.727259121644143 0.727988932112673
1 1 1 1
0.73253590847921 0.733050969581372 0.73585341018303 0.736100910077105
1 1 1 1
0.736264378588264 0.736396056649703 0.736733672969515 0.736890752775714
1 1 1 1
0.73901319571541 0.739198152742966 0.743063411228993 0.743123362736312
1 1 1 1
0.743229186021581 0.746556019528694 0.749453594924348 0.749684101050094
1 1 1 1
0.752661616517319 0.752921360169034 0.754208614275264 0.755018297383795
1 1 1 1
0.755826600512071 0.755932942064431 0.758935176438243 0.759014490578655
1 1 1 1
0.759387104906326 0.760390639929013 0.761128953781793 0.761154058609079
1 1 1 1
0.762092599957873 0.764253747231253 0.764743128454422 0.76511636361788
1 1 1 1
0.766135089686585 0.767763749496715 0.768360150856037 0.76900778082332
1 1 1 1
0.769178815041881 0.769591270156107 0.770239909670681 0.771753602475904
1 1 1 1
0.772557140487059 0.774798141312558 0.778784531855193 0.780462418825799
1 1 1 2
0.780485282977442 0.780749450530182 0.780802763952365 0.78170641882494
1 1 1 1
0.781774812387549 0.782001809300324 0.782320886084968 0.785395315543136
1 1 1 1
0.785539119721115 0.785729146035225 0.786342552124678 0.787486487593124
2 1 1 1
0.790584080290573 0.790688550929004 0.791334555727284 0.79189767431877
1 1 1 1
0.792504760884445 0.792575531394977 0.793697102608643 0.793887164398902
1 1 1 1
0.794068062834576 0.794173093760284 0.79561235332347 0.796181631820803
1 1 1 1
0.796822366642249 0.798273811705353 0.798990942085597 0.800682809935844
1 1 1 1
0.800751999282176 0.801413402397465 0.801520157762847 0.8024393871435
1 1 1 1
0.80570653724526 0.805880762335817 0.808136667525012 0.811796318011659
1 1 1 1
0.812880823651925 0.813331181230054 0.816490344105899 0.817370887898084
2 1 1 1
0.817539470901282 0.821355259618999 0.82158026385131 0.822211586476477
1 1 1 1
0.824608560844549 0.824701058337861 0.826145679173987 0.827208412198468
1 1 1 1
0.828419586680114 0.829794032837609 0.831612173421495 0.833242562921642
1 1 1 1
0.83368858192509 0.835587945991177 0.836002595242194 0.836763584184259
1 1 1 1
0.837094406296968 0.837704937191438 0.838492578988438 0.838897894204217
1 1 1 1
0.83968092685975 0.839842777617805 0.841397868543514 0.84241424643268
1 1 1 1
0.842460261232891 0.842505015675404 0.843942472460158 0.845915919238962
1 1 1 1
0.846156349705936 0.847440269638739 0.848843907657719 0.849295802177984
1 1 1 1
0.850825051617427 0.85237714215807 0.853025157247767 0.854050903413181
1 1 1 1
0.855638957450778 0.856594456016856 0.856672922225895 0.858623597333042
1 1 1 1
0.859307739394666 0.859638865921182 0.86153388870288 0.863207485785994
1 1 1 1
0.864327793438094 0.864780268382673 0.864792118708709 0.865367110555197
1 1 1 1
0.865868467899835 0.866026334173109 0.870275070691238 0.870938186266881
1 1 1 1
0.871009926302234 0.871390970848139 0.87176691963042 0.872142031753177
1 1 1 1
0.873068405951979 0.873168978803444 0.875712651420304 0.875956810262953
1 1 1 1
0.876518398766251 0.876746967220114 0.878748495769536 0.879228514992745
1 1 1 1
0.880042581219496 0.881551407747888 0.881585985877426 0.882162121264921
1 1 2 1
0.882944066104863 0.882993399808462 0.883842170339704 0.887061872854083
1 1 1 1
0.88956816338117 0.890671197914167 0.891438108316994 0.892982138626283
1 1 2 1
0.895029646108037 0.895586927624849 0.896949551462331 0.897572079590053
1 1 1 1
0.897636798915308 0.898824108631426 0.899018226205464 0.902224675145764
1 1 1 1
0.90388137138137 0.90442181680672 0.904522947655554 0.904868531850856
1 1 1 1
0.905160140075085 0.905199131734037 0.907908603214167 0.909985222888397
1 1 1 1
0.910369634704683 0.911358324634709 0.913417656302524 0.913442355343472
1 1 1 1
0.914307554199252 0.914906231894298 0.915005006079473 0.916083816009661
1 1 1 1
0.916821997818062 0.918738165713602 0.922347055027604 0.922722689357831
1 1 1 1
0.923638150290761 0.923652303739677 0.923993749516485 0.924533514811105
1 1 1 1
0.92599045709692 0.926698046891224 0.92738734016936 0.927749112970918
1 1 1 1
0.929156654982786 0.929449821044403 0.931717468279045 0.932154940125562
1 1 1 2
0.934154831810681 0.935250813364141 0.935381498883791 0.935513973972908
1 1 1 1
0.936393826004722 0.937070644423922 0.939900007412363 0.941057195281254
1 1 1 1
0.941736997115192 0.94368595285946 0.943752748312622 0.943862472006647
1 1 1 2
0.944317018423498 0.945532123516936 0.945776091661955 0.946462096986349
1 1 1 1
0.949054041044226 0.95084593131949 0.951355920183733 0.95685018419563
1 1 1 1
0.95905223165969 0.959867998806135 0.962093477219855 0.962432839898271
1 1 1 1
0.96298289106909 0.964407547069204 0.965845502646825 0.970318631551722
1 1 1 1
0.973900838979688 0.973968772650075 0.974844088071628 0.977686214244416
1 1 2 1
0.97803666052813 0.978685992340487 0.980275969155502 0.980716020907018
1 1 1 1
0.98109326655663 0.98291961454063 0.983203197778922 0.986080197106396
1 1 1 1
0.987462962809093 0.98798219761531 0.988778254298348 0.990112883629133
1 1 1 1
0.990466191421899 0.990801843714705 0.990993793684525 0.995690103399442
1 1 1 1
0.997262509714786 0.997800602576348 0.99900850683577
1 1 2 print(paste("Media:", media))[1] "Media: 266.367857142857"print(paste("Mediana:", mediana))[1] "Mediana: 270.5"print(paste("Moda:", moda))[1] "Moda: 0.71945240936513"print(paste("Varianza:", varianza))[1] "Varianza: 23290.9020061334"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 152.613570845234"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 531"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.17946448700023"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0.00149753601147101"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles) 25% 50% 75%
135.75 270.50 397.25 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55%
26.95 54.90 82.00 108.80 135.75 161.70 188.65 216.60 243.55 270.50 288.45
60% 65% 70% 75% 80% 85% 90% 95%
316.40 342.35 369.30 397.25 425.20 451.15 479.10 505.05 De este histograma, se infiere que la distribución de esta variable no es normal, y además, está sesgada hacia la derecha.
Para Recall:
library(e1071)
library(dplyr)
variable <- dataset$Recall
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
hist(frecuencia, main="Distribución de la Variable Recall",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
0.30009428510314 0.300947538000828 0.301095573634031 0.302673945861008
1 1 1 1
0.303054288755216 0.305489113540342 0.306204299579428 0.306326928355505
1 1 1 1
0.306946674789485 0.30709182881942 0.308194627511633 0.308472181743275
1 1 1 1
0.310020694366942 0.310285372058468 0.311863365422707 0.31228665435664
1 1 1 1
0.313381266100835 0.313529341642321 0.31634646742973 0.31651647525187
1 1 1 1
0.317813431934026 0.319275703908626 0.320418834551685 0.32166905364354
1 1 1 1
0.325213172803998 0.327250974327967 0.327297208802438 0.327621673023629
1 1 1 1
0.330729959850104 0.331437909296931 0.333730208675307 0.334985320061775
1 1 1 1
0.335158208024782 0.33579476700947 0.336648514131231 0.338032424376033
1 1 1 1
0.340491114613012 0.340664366456245 0.34166729024344 0.343542258315292
1 1 1 1
0.34372031553335 0.345986401268056 0.346206890898169 0.346510691049042
1 1 1 1
0.349705365173279 0.350198322193356 0.350243064358559 0.350621532680557
1 1 1 1
0.351031284757532 0.35115709341891 0.352923528431725 0.353367452581495
1 1 1 2
0.353803452693314 0.354354534270123 0.356126009857332 0.362023299778775
1 1 1 1
0.362502667167901 0.366779494119247 0.371262578064676 0.37132467164621
1 1 1 1
0.373755445575599 0.376484947216735 0.37769866915392 0.378058548624894
1 1 1 1
0.380141346646134 0.381297272140368 0.382951836518706 0.384145060384403
1 1 1 1
0.384390891482583 0.384717500339635 0.386044474925771 0.386102306586622
1 1 1 1
0.387057879300357 0.387374569776794 0.387885150333857 0.391456640676424
1 1 1 1
0.393679854099785 0.393992395631593 0.394104590585685 0.395620632555821
1 1 1 1
0.397437690941987 0.398387077304853 0.398562064224873 0.39949598665542
1 1 1 1
0.399815900857336 0.399995201110587 0.400013172937588 0.402873896711747
1 1 1 1
0.403112130995279 0.404157178583581 0.407901530224941 0.412017455524236
1 1 2 1
0.413170005365873 0.413889820665996 0.416024845874109 0.416802141189127
1 1 1 1
0.416867162123039 0.422655240474079 0.430295128427344 0.433075354848609
1 1 1 1
0.434115062014378 0.43623668569341 0.437083158893989 0.4378479931174
1 1 1 1
0.439450692425837 0.440332160869882 0.440918475475703 0.442256163760261
1 1 1 1
0.443276076340099 0.444953066447599 0.446217906803615 0.44642982578555
1 1 1 1
0.447493474707042 0.448395838289061 0.451018475423518 0.452524787978493
1 1 1 1
0.454596948074106 0.455453109485324 0.457766887604736 0.4582202984712
1 1 1 1
0.459424815272247 0.459764754445589 0.460073745722526 0.462669026139233
1 1 1 1
0.468279239025455 0.469325305879022 0.469352176220871 0.469383991221932
1 1 1 1
0.472622544484617 0.472776708441332 0.473138221073358 0.47570096828361
1 1 1 2
0.480325054233605 0.481534428121966 0.481679248223263 0.481933485469983
1 1 1 1
0.48731487370958 0.489275300469168 0.4899865663127 0.492292670533524
1 1 1 1
0.492766821978793 0.49303729777595 0.49331869047463 0.495131910690187
1 1 1 1
0.496703149236099 0.497735120783919 0.497747246180997 0.498991865049262
1 1 1 1
0.500048488868109 0.501186717525906 0.501883806473122 0.502219457236416
1 1 2 1
0.502471340380858 0.503353153969994 0.505316027546395 0.506233577442335
1 1 1 1
0.506528495357909 0.50670334583356 0.506711034300283 0.50863654604761
1 1 1 1
0.509576911860177 0.509695974567712 0.509860369295665 0.511633274546046
1 1 1 1
0.512041010183235 0.514419449144749 0.517852246544375 0.518304700541818
1 1 1 1
0.5193435423096 0.519776702164147 0.520939140634345 0.521389104810515
1 1 1 1
0.522310756682782 0.523206772824797 0.525046990873517 0.525168992761684
1 1 1 1
0.532095289347036 0.536141882738365 0.538270972978154 0.538422916606904
1 1 1 1
0.539713585184299 0.540217147220861 0.541634545945947 0.5421142225165
1 2 1 1
0.543093927321355 0.544174373778636 0.547135274120212 0.548339904285189
1 1 1 1
0.549920540779009 0.550469858879484 0.551100867791909 0.552035326130685
1 1 1 1
0.552163743160299 0.553343993586505 0.555215609738278 0.55597652378296
1 2 1 1
0.557450191429307 0.558095019605357 0.558337115232642 0.558869279191024
1 1 1 1
0.559820696406339 0.56020684648164 0.560217506434431 0.562187020914085
1 1 1 1
0.562730935543721 0.564122637774235 0.565365834070355 0.568687218131486
1 1 1 1
0.56894469909006 0.569858333315846 0.570578354776119 0.571354163818953
1 1 1 1
0.571715994288897 0.576596420285023 0.57848563785151 0.578603705068152
1 1 1 1
0.581245160458027 0.582011297842846 0.583002823078408 0.583571886169296
1 1 2 1
0.585280121722701 0.585308946001672 0.586740226426662 0.589549872443045
1 1 1 1
0.591553102332715 0.593263453131233 0.593613595770119 0.595423982089347
2 1 1 1
0.600091414690503 0.600951754173104 0.601370536923545 0.601689654359307
1 1 1 1
0.602910395213793 0.602971201546628 0.603672193703571 0.605629932838136
1 1 1 1
0.605897119965935 0.607404871643624 0.608308945218697 0.610830624441542
1 1 1 1
0.611879147119324 0.613371397787293 0.613823338758596 0.614544819427749
1 1 2 1
0.61780113483728 0.619365556268879 0.620389723611506 0.6205970313025
1 1 1 1
0.620966106217324 0.621765409281863 0.623872923545775 0.624866611617453
1 1 1 1
0.628991787710556 0.630597262914087 0.631666879878563 0.632882226240779
1 1 1 1
0.633505890440654 0.633790427822472 0.633830074527579 0.636623102622106
1 1 1 1
0.638385205181203 0.638853948797141 0.640200345658322 0.641339466767048
1 1 1 1
0.642228482254716 0.644627836000827 0.645005209113213 0.64566982831985
1 1 1 1
0.647686795972563 0.648277896502272 0.649279349249706 0.650280801997141
1 1 10 1
0.650422499808295 0.650436987649292 0.652158765545885 0.653818582537315
1 1 1 1
0.654170535414452 0.657790397466061 0.657892823540526 0.66110333189863
1 1 1 1
0.661688869658387 0.662572369398805 0.663322596090684 0.664118924617526
1 1 1 1
0.664907233357897 0.66502174710503 0.665803619535722 0.670761806761934
1 1 1 1
0.671656374888466 0.673370640135754 0.673777230783435 0.67898532514331
1 1 1 1
0.679193368687003 0.680117208770364 0.681137632960184 0.682603999422606
1 1 1 1
0.687598039750608 0.690396178375031 0.691049677515298 0.694851820183462
1 1 1 1
0.695559718716929 0.698564152827598 0.698677845696973 0.703985810226824
1 1 1 1
0.704039920714186 0.704095320463192 0.704808879594252 0.706062184268618
1 1 1 1
0.706327320695587 0.707135605092435 0.70753912261588 0.710105351917463
1 1 1 1
0.712112065491924 0.713791212280962 0.71549265476515 0.715562553845977
1 1 1 1
0.716592172433977 0.720751916760163 0.722060013535623 0.722445167230365
2 1 1 1
0.724045474616883 0.725426485576906 0.728801427841373 0.729522879966221
1 1 1 1
0.734462335877209 0.735640285232072 0.735689549096198 0.736384170711608
1 1 1 2
0.737348703952582 0.738364024994745 0.738614757765247 0.740690387824215
1 1 1 1
0.741645253160414 0.742898315124021 0.744054582210181 0.74516829501461
1 1 1 1
0.745267232486679 0.74583162221832 0.748333229523091 0.748430628484221
1 2 3 1
0.750904455033141 0.75138282281562 0.752075670400539 0.752521119146551
1 1 1 1
0.75347221219337 0.756147832334094 0.756604154014358 0.759641751595513
1 1 1 1
0.76014743751909 0.760978360969038 0.763703808190748 0.766469789504745
1 1 1 1
0.766620335332633 0.76800085270604 0.771076635676103 0.771891206875244
1 1 1 1
0.773984447814506 0.774279587221267 0.774469240217031 0.775068969670795
1 1 1 1
0.775734232914575 0.777832054856382 0.780612939444825 0.78091348655227
1 1 1 1
0.781405429701392 0.781791965046166 0.781883512944496 0.784744978668458
1 1 1 1
0.784772702075976 0.791778351074365 0.792699964144032 0.793910103850677
1 1 1 1
0.794883541219001 0.794960534086689 0.795404945187269 0.798205964022234
1 1 1 1
0.799132235444023 0.799244818297832 0.799766842754613 0.802831822760403
1 1 1 1
0.805500264819134 0.80589487038876 0.810203009588963 0.810421441284614
2 1 1 1
0.816508662993071 0.817018220692632 0.818333292367463 0.81863283930645
1 1 1 1
0.823211084617686 0.82405166388834 0.825824633465893 0.827399545579878
1 1 1 1
0.827985481342916 0.829349529765124 0.830117144994107 0.831143377630128
1 2 1 1
0.832705546446774 0.832726453175548 0.833258733964388 0.833331268823409
1 1 2 1
0.835169456258302 0.83628115295691 0.837297339962543 0.838245947475349
1 1 1 1
0.839110748229967 0.840138837685025 0.841045037313281 0.84119931174307
1 1 1 1
0.841793964706934 0.842742305282195 0.846255852104817 0.846263286499686
1 1 1 1
0.846925299023114 0.847276704341455 0.848238889309038 0.849632680203886
1 1 1 1
0.851284360101145 0.852252730243205 0.852289611944555 0.853356855992419
1 1 1 1
0.854816581401868 0.855200011797718 0.855947463784584 0.856160881143524
1 1 1 1
0.858866238362847 0.862437920307819 0.862770955286764 0.863106045375653
1 1 1 1
0.864875843618796 0.865008876155418 0.865764647006456 0.86778663895343
1 1 1 1
0.874838797785159 0.875525920771496 0.875695661567795 0.875774356068938
1 1 1 1
0.876653268954906 0.878695151819041 0.879263245474412 0.88355497335631
1 1 1 1
0.883901217900473 0.884836158019536 0.887536944649202 0.889898331512388
1 1 1 1
0.890554764836277 0.891923054092935 0.892145007774412 0.892878197944942
1 1 1 1
0.89294257888873 0.893629462721039 0.895243600783927 0.897649445193267
1 2 1 1
0.897773376868795 0.898521141133955 0.900293636362899 0.904483265760182
1 1 1 1
0.905904001937186 0.9067392481542 0.908978411753379 0.911589015426441
1 1 1 1
0.913963406712732 0.91610971654504 0.916220333504249 0.918425334090242
1 1 1 1
0.921882570616077 0.922061356185779 0.923067924628666 0.92309879617721
1 1 1 1
0.923150501845322 0.924310501367514 0.924790759240532 0.92516314363679
1 1 1 1
0.925866011773276 0.928992423272387 0.931717315100089 0.934277701492748
1 1 1 1
0.935529155645733 0.936960200698074 0.939300863303366 0.941644665088845
1 1 1 2
0.942240090192393 0.942767360672806 0.942898502501786 0.943671717259235
2 1 1 1
0.948335847902247 0.948467824711061 0.950459637542298 0.959207998133248
1 1 1 1
0.959907023365879 0.960591114974155 0.960829465677778 0.962519559205284
1 1 1 1
0.96338161817513 0.965321419402707 0.965540895411937 0.965650016151784
1 1 1 1
0.966000867253282 0.968542358039492 0.968580645104191 0.969143180268723
1 1 1 1
0.969233000528353 0.969759870839 0.970213613326667 0.970452860691743
1 1 1 1
0.970553884739739 0.972094923083813 0.97243888285924 0.972794839785315
1 1 1 1
0.973937845177244 0.974449468621312 0.974812184982392 0.97482019301586
1 1 1 1
0.974854891543076 0.976233253590074 0.976492170106485 0.98193611067145
1 1 1 1
0.983209676295449 0.984115535594053 0.985286780622366 0.986517540508401
1 1 1 1
0.98669116471388 0.986800612254275 0.986824485733606 0.986834770414881
1 1 1 1
0.988809214247325 0.991625176308914 0.993929531094954 0.995278510796075
1 1 1 1
0.995693872229789 0.996373505776166 0.998474598977385
1 1 1 print(paste("Media:", media))[1] "Media: 266.821428571429"print(paste("Mediana:", mediana))[1] "Mediana: 271"print(paste("Moda:", moda))[1] "Moda: 0.649279349249706"print(paste("Varianza:", varianza))[1] "Varianza: 22891.4134934833"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 151.299086228183"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 531"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.16814930781372"print(paste("Asimetría:", asimetria))[1] "Asimetría: -0.0094400805535875"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles) 25% 50% 75%
137.75 271.00 395.25 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55%
28.95 55.90 83.85 110.80 137.75 164.70 191.65 218.60 243.55 271.00 290.45
60% 65% 70% 75% 80% 85% 90% 95%
317.40 341.35 369.30 395.25 422.20 450.00 477.10 503.05 De este histograma, se infiere que la distribución de esta variable no es normal, y además, está sesgada hacia la derecha.
Para F1_Score:
library(e1071)
library(dplyr)
variable <- dataset$F1_Score
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
hist(frecuencia, main="Distribución de la Variable F1_Score",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
0.40000698085322 0.400884293251787 0.401195281131442 0.403188085401008
1 1 1 1
0.404991965336315 0.405018209126114 0.405432496948223 0.40598726599507
1 1 1 1
0.406850790072444 0.407294062886432 0.408247332406807 0.408628867643251
1 1 1 1
0.409066410528685 0.409236935014785 0.410874424627438 0.411477379862372
1 1 1 1
0.413147997265005 0.413455533497233 0.415116048375538 0.418689455676035
1 1 1 1
0.420205842324678 0.422542654239345 0.423362810012599 0.423387592396678
1 1 1 1
0.42421049611582 0.425453378924135 0.431001232994777 0.431101479471837
1 1 1 1
0.432780652000583 0.433705646408463 0.433951393688029 0.43463929553507
1 1 1 1
0.437515777445708 0.438403807965173 0.439877995465763 0.439938836748534
1 1 1 1
0.440184167215163 0.440353548380421 0.440501528010293 0.441011920185975
1 1 1 1
0.441075231600147 0.441228206634377 0.44140455556769 0.44142754378876
1 1 1 1
0.442295167385887 0.44269497110406 0.44446325354492 0.44535016831244
2 2 1 1
0.445419836385873 0.446183001628524 0.44618768023898 0.447073489790274
1 1 1 1
0.448689507121743 0.450132602506414 0.453030968190711 0.455240191649485
2 1 1 1
0.45557528983082 0.456950762093002 0.460823738531896 0.461135860523762
1 1 1 1
0.461509578439885 0.461540777550154 0.463235930864683 0.463543482642255
1 1 1 1
0.466259118046662 0.467982102836479 0.469236785307351 0.47032234340814
2 1 1 1
0.470530780090132 0.476720080733451 0.478048401897368 0.479029017147456
1 1 1 1
0.484194710916109 0.485705178888599 0.49095704488006 0.492897167558632
1 1 1 1
0.49388602960216 0.494363924907829 0.495695357524815 0.496219243671846
1 1 1 2
0.496277568562736 0.49681768063323 0.497821202158955 0.499170694085775
3 1 1 1
0.499448906179133 0.500392782400636 0.501928603630441 0.50301634462327
1 1 1 1
0.507551953443569 0.507553367144674 0.507618809207326 0.508968380653962
1 1 1 1
0.510065317842061 0.511388022940746 0.512633443415351 0.512752228489194
1 1 1 1
0.514555951042986 0.516317840762136 0.516985119940174 0.519395283375662
1 1 1 1
0.519562201880081 0.520169210720576 0.521352508314721 0.521579580481206
1 1 1 1
0.522083645498558 0.522589830039382 0.52319976322408 0.523751268301692
1 1 1 1
0.526981539141917 0.528643889795899 0.528947582221837 0.530600439748322
1 1 1 1
0.531229367798756 0.531732353937881 0.533416782848902 0.534576089971027
1 1 1 1
0.535675198749803 0.537325277490099 0.537758896452381 0.53824999727041
1 1 2 1
0.539210908185286 0.540522022555801 0.540984042997572 0.544897891154121
1 1 1 1
0.5449003767957 0.544922105021009 0.545213247988526 0.546038009931118
1 1 1 1
0.547211388499727 0.548535862167932 0.54902575622188 0.549030165245925
1 1 1 1
0.549405241665454 0.550280739275499 0.550535827414661 0.551860923507765
1 1 1 1
0.551963430113629 0.555226985293265 0.555745869565029 0.556141958791138
1 1 1 1
0.558437190816231 0.558565757895184 0.558781016155214 0.55919568253328
1 1 1 1
0.560441216714525 0.561120253640564 0.561312108629316 0.561707117375364
1 1 1 2
0.562483796822184 0.562565618989819 0.56265775225844 0.563167623651069
1 1 1 1
0.564442953605315 0.565791465079512 0.566711665653827 0.569483455822002
1 1 1 1
0.571454994755624 0.57247699893835 0.572579637426207 0.57351246777757
1 1 1 1
0.574027319177462 0.575429866247316 0.577935947323558 0.5783744741844
1 1 1 1
0.580627646700588 0.581758543384258 0.582365507353016 0.582519231781769
1 1 1 2
0.584065959713285 0.584677499008447 0.585884125193481 0.587666793526212
1 1 1 1
0.587744436528189 0.588296084934649 0.592697291581572 0.593816407452456
1 1 1 1
0.594707080105205 0.595174371017049 0.595177080413819 0.595983549655547
1 1 1 2
0.596045525218025 0.599314619869363 0.599473694289227 0.600177037502119
1 1 1 1
0.600429979401262 0.601366272561906 0.602323945339451 0.605143166863294
1 1 1 1
0.607205171346933 0.607914500771631 0.610312320571697 0.611775102071414
1 1 1 2
0.612273495241862 0.612562796330329 0.612654969275833 0.614131585102666
1 1 1 1
0.616256096284892 0.621008328276611 0.621069351949947 0.621568462129325
1 1 1 1
0.621744519656064 0.622667763058077 0.623519964255731 0.624352628207688
1 1 1 1
0.6252813570799 0.628310625921937 0.629679258661833 0.630613023114481
1 1 1 1
0.632695653950159 0.633538283015073 0.633642963387325 0.634619721476439
1 1 1 1
0.635115623912816 0.63563844596285 0.635917120616753 0.637932209193978
1 1 1 1
0.638567427131722 0.639421190585461 0.642160601416955 0.642716431344322
1 1 1 1
0.644891014520019 0.645647243090211 0.645802632025596 0.646714910796752
2 1 1 1
0.647174857020461 0.649939497089375 0.651000318461368 0.651562996699613
1 1 1 1
0.653577518208166 0.653637182136359 0.654910505720852 0.655136911262616
1 1 1 1
0.656560800222002 0.657366600058087 0.659211356556704 0.659407735842008
1 1 1 1
0.659660127759558 0.660083339653381 0.660149675579569 0.660412583625255
2 1 1 1
0.660641991403966 0.662596796888922 0.66352636074983 0.665376283270681
1 1 1 1
0.665527308888847 0.666351672703827 0.670152547685734 0.670776467817553
1 1 1 1
0.672607253840593 0.675364309958092 0.677029686287872 0.678543111843535
1 1 1 1
0.679785853684102 0.684352732069662 0.684553012586172 0.689823818535334
1 2 1 1
0.690393620907848 0.691056795987724 0.694657437629899 0.697755251729417
1 1 1 1
0.700067651245976 0.701578745578078 0.701879483530924 0.702877358982717
1 1 1 1
0.703380492053175 0.704152262777101 0.704235788043231 0.704683038375267
1 1 1 1
0.705334333354634 0.708312678524061 0.708636344236008 0.708960009947956
1 1 10 1
0.709003395825834 0.710804839842775 0.711220596628357 0.711534742468123
1 1 1 1
0.712869414500128 0.713506108651353 0.716606479733017 0.719502439849589
1 1 1 1
0.721332288927804 0.721393959608547 0.722999165953428 0.723456731641605
1 1 1 1
0.724543002302849 0.725056578560538 0.726552379668219 0.726698175462319
1 1 1 1
0.727858189646708 0.729051497796138 0.731624245431127 0.732022713849863
1 1 1 1
0.734127065903257 0.734402301743805 0.735435570967961 0.73640697696337
1 1 1 1
0.738037210427584 0.739708414735043 0.743047589886249 0.746021439314654
1 2 1 1
0.747284052707164 0.748570227932908 0.749755634082558 0.750228152638818
1 1 1 1
0.750669345854456 0.752161903935344 0.752551522665641 0.753672393690818
1 1 1 1
0.754382700396783 0.757181959556493 0.758111126132656 0.758293183594181
1 1 1 1
0.758600969621622 0.759426752290229 0.760932327579894 0.762182320335625
1 1 1 1
0.763382733594047 0.764039034830462 0.764651609857392 0.766004450247691
1 1 1 1
0.766328053009255 0.767975010932427 0.769780291555434 0.770070164711525
1 1 1 1
0.771715720021782 0.772284271031182 0.772775469429766 0.77418926697416
1 1 1 1
0.774245850918405 0.774924459764199 0.777055873968752 0.778148331673695
1 1 1 1
0.778851352731026 0.779369292182584 0.779434794597032 0.781824568920025
1 1 1 1
0.782612948137561 0.785040638379135 0.788990804471257 0.789102892071213
1 1 1 1
0.789593394746129 0.792479642216724 0.792605203295632 0.792790412119573
1 1 1 1
0.793104228714603 0.794037690832965 0.794053638084734 0.795706461184462
1 1 1 1
0.796608552548392 0.797010573039914 0.797181366876321 0.797828315082054
1 1 1 1
0.798531630993381 0.799877828516101 0.802694484027813 0.802887489200324
1 1 1 1
0.803476298815017 0.803621796525339 0.803723001158848 0.804187250484945
1 1 1 1
0.804411951435276 0.805615772831529 0.806164469798102 0.808067131268184
1 1 1 1
0.811266329933141 0.813178977584725 0.815244188214621 0.815415353476635
1 1 1 1
0.816170834484277 0.816369754306094 0.816757256351971 0.816784575336237
1 1 1 1
0.817693687082755 0.818325629145782 0.819369297092431 0.820683756650484
1 1 1 1
0.820701916954156 0.821287657709098 0.822219867777431 0.822732656816467
1 1 1 1
0.822922606026029 0.823276498170092 0.823977921927226 0.824438200019757
1 1 1 1
0.825259393137493 0.825592497083566 0.827572799859108 0.828431634026876
1 1 1 1
0.828595981440999 0.828654498442745 0.829838267174859 0.83107236839353
1 1 1 1
0.831243770712118 0.834066197412947 0.834068690710001 0.836234056969234
1 1 1 1
0.83738863699349 0.837606876452798 0.839440629435027 0.839619430354168
1 1 1 1
0.839640084871699 0.840666359245355 0.841921137000876 0.842730990900764
1 1 1 1
0.842750436012415 0.84323389043594 0.845351912319452 0.845728896200763
1 1 1 1
0.849030609805739 0.850563879017991 0.851048195437504 0.852548955809248
1 1 1 1
0.854038100241141 0.855229192698352 0.855403169513159 0.856510798558469
1 1 1 1
0.857381574700576 0.858612031861856 0.858664436845303 0.859328050309517
1 1 1 1
0.859909029719551 0.862673689511132 0.863685743974203 0.866815145886792
1 1 1 1
0.868379030455334 0.869175986294775 0.870242950645142 0.870255905490464
1 1 2 1
0.871723391356635 0.8724322160514 0.873575708991811 0.874934921554822
1 1 1 2
0.875654868143688 0.877744870324821 0.878008838314823 0.880002089058209
1 1 1 1
0.882288727116068 0.882696785459093 0.883054191097398 0.88399903181609
1 1 1 1
0.884016111816843 0.884242542320022 0.886527148604751 0.888475411354697
1 1 1 1
0.888963837124324 0.890067679903382 0.890276885209351 0.892833017740417
1 1 1 1
0.893098567951216 0.89379028302506 0.894845942408205 0.895249398474369
1 1 1 1
0.896503791923933 0.897133358743649 0.899698226072963 0.90149555674631
1 1 1 1
0.902271776698391 0.902745024911082 0.903095100305815 0.903398396630806
1 1 1 1
0.903880963998656 0.906922808653137 0.909055227454315 0.912984411736885
1 1 1 1
0.913922334248756 0.914813962604338 0.915258567609683 0.915290062700893
1 1 1 1
0.917014542272407 0.917584282689507 0.919177455345347 0.92231617976163
1 1 1 1
0.925529850110234 0.925791659885387 0.926410271879703 0.926482027992689
1 1 1 1
0.927511463560749 0.929014367106105 0.929796294897864 0.932870913360421
1 1 1 1
0.933476754364006 0.934245710331597 0.934513320989888 0.937207653491902
1 1 1 1
0.9387515121746 0.940576537414281 0.941064417127737 0.94116411804949
1 1 1 1
0.943652236288756 0.944703108330121 0.944937093220194 0.948273066323956
1 1 1 2
0.948729198309135 0.952459965078014 0.952596712657946 0.956266377315056
1 1 1 1
0.956909258868371 0.957483712009278 0.959626304879657 0.959754917541803
1 1 1 1
0.961768372881356 0.963441087670175 0.964470712301865 0.964672487520204
1 1 1 1
0.966669149616582 0.966841755269848 0.968040237354037 0.968254400265111
1 1 1 1
0.97085393250734 0.970894426106072 0.971333071418557 0.971689010201504
1 1 1 1
0.97454860905029 0.975917681628073 0.979009221672683 0.980107299879571
1 1 1 1
0.980221165153688 0.980839487230455 0.981122399019935 0.982154265835634
1 1 1 1
0.982405927245847 0.9838468977834 0.986204172663366 0.987115281033484
1 1 1 1
0.988221244565311 0.990915041657485 0.99440749423946 0.997694604099267
1 1 1 1
0.99830941234177 0.998576978441294 0.999335567219974
2 1 1 print(paste("Media:", media))[1] "Media: 263.9875"print(paste("Mediana:", mediana))[1] "Mediana: 265.5"print(paste("Moda:", moda))[1] "Moda: 0.708636344236008"print(paste("Varianza:", varianza))[1] "Varianza: 23249.568716458"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 152.478092578763"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 531"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.18497413441012"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0.0260643350153632"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles) 25% 50% 75%
132.75 265.50 395.25 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55%
28.95 53.90 80.00 105.80 132.75 159.70 185.65 212.60 238.55 265.50 284.45
60% 65% 70% 75% 80% 85% 90% 95%
311.40 339.35 367.30 395.25 423.20 449.15 477.10 504.05 De este histograma, se infiere que la distribución de esta variable no es normal, y además, está sesgada hacia la derecha.
Para Training_Time:
library(e1071)
library(dplyr)
variable <- dataset$Training_Time
#Frecuencia
frecuencia <- table(variable)
#Medidas de tendencia central
media <- mean(as.numeric(factor(variable)), na.rm = TRUE)
mediana <- median(as.numeric(factor(variable)), na.rm = TRUE)
moda <- names(which.max(table(variable)))
#Medidas de dispersión
varianza <- var(as.numeric(factor(variable)), na.rm = TRUE)
desviacion <- sd(as.numeric(factor(variable)), na.rm = TRUE)
rango <- range(as.numeric(factor(variable)), na.rm = TRUE)
#Curtosis y Asimetría
curtosis <- kurtosis(as.numeric(factor(variable)), na.rm = TRUE)
asimetria <- skewness(as.numeric(factor(variable)), na.rm = TRUE)
# Distribución de frecuencias usando gráfico de barras
hist(frecuencia, main="Distribución de la Variable Training_Time",
xlab="Categorías", ylab="Frecuencia", col="gray")
#Percentiles y cuartiles
cuartiles <- quantile(as.numeric(factor(variable)), probs = c(0.25, 0.5, 0.75), na.rm = TRUE)
percentiles <- quantile(as.numeric(factor(variable)), probs = seq(0.05, 0.95, by = 0.05), na.rm = TRUE)
print("Frecuencia:")[1] "Frecuencia:"print(frecuencia)variable
0.103201614730368 0.131257312692294 0.133702014876282 0.150394030084891
1 1 1 1
0.152974309812462 0.15538242928621 0.18130315509973 0.1938098531845
1 1 1 1
0.193861879201139 0.21616799285814 0.222361144373543 0.240396895130507
1 1 1 1
0.247127426114025 0.247508973835463 0.249272062913905 0.255544450327644
1 1 1 1
0.258972885631216 0.26002939784403 0.271066608015497 0.292420129784096
1 2 1 1
0.293019985094815 0.296289683348403 0.297264214745237 0.305384561909662
1 1 1 1
0.343110429360304 0.346190748132613 0.346712682149831 0.347808208738721
1 1 1 1
0.348050114118463 0.351339860007956 0.354747824690767 0.358549763512053
1 1 1 1
0.372467056234257 0.379195762287105 0.402861457377191 0.405730936131558
1 1 1 1
0.406567726875313 0.424209425288758 0.428381034980929 0.42944748244375
1 1 1 1
0.443529884242159 0.44807095631561 0.476334936740666 0.486803074438122
1 1 1 1
0.503134388957603 0.505410494529131 0.509272081932092 0.512225545070976
1 1 1 1
0.514370352676465 0.514972875189003 0.517007081986948 0.526384369683665
1 1 1 1
0.552566587745755 0.559504978659381 0.567268514237717 0.591203262242096
1 1 1 2
0.594792723407029 0.605998543487737 0.611827138690742 0.618784159244334
1 1 1 1
0.646805699790513 0.67015657730603 0.671257065322914 0.681354452133744
2 1 1 1
0.681674567994646 0.687466358016289 0.689899136066536 0.714882854315838
1 1 1 1
0.717409936533572 0.735426993298753 0.763751730293985 0.772027591948442
1 1 1 1
0.791995362528432 0.800705501062059 0.805986051464678 0.817537657353799
1 1 1 1
0.819917425560477 0.821650261405246 0.837314127929388 0.84503798038001
1 1 1 1
0.853086109936602 0.857011799624136 0.865412186564448 0.868382256052348
1 1 1 1
0.885105444784881 0.887329965088041 0.889972178678101 0.890700056103077
1 1 1 1
0.897675847110524 0.898793657692943 0.905587092486506 0.920049457960227
1 1 1 1
0.920706336561128 0.924197913255939 0.931669300026923 0.936470980231153
1 1 1 1
0.937588371862157 0.945366997037174 0.950130646739608 0.958103386638731
1 1 1 1
0.959908974168651 0.978844450417281 0.987798067345406 0.990716449365073
1 1 1 1
0.995905121357204 1.00469904100211 1.00782474137829 1.01009205282541
1 1 1 1
1.0339881820648 1.05631593437139 1.06245415777288 1.0636025662695
1 1 1 1
1.10179702507494 1.11695058740795 1.12439093116355 1.13148400436018
1 1 1 1
1.13288619759514 1.13451711853438 1.13503597421736 1.14099165825782
1 1 1 1
1.15200984857044 1.16921691930564 1.17167802158556 1.18018542080255
1 1 1 1
1.18047089083467 1.18406961258571 1.19111278770312 1.19916093838228
1 1 1 1
1.20778744795176 1.20995596757692 1.2238923074846 1.22615095640833
1 1 1 1
1.23376511824655 1.23422854744996 1.23927936181837 1.24568288215601
2 1 1 1
1.24868544005642 1.26097329204258 1.26364492808606 1.26691860296191
2 1 1 1
1.30862721744649 1.32337786842713 1.33072941098717 1.33900477942555
1 1 1 1
1.3511482314399 1.35666899898215 1.37238711085703 1.38991199793826
1 1 1 1
1.40093239640245 1.40304940809738 1.41595462052285 1.43031081245929
1 1 1 1
1.43100258824441 1.43279316618734 1.44083804751778 1.44867198708134
1 1 1 1
1.44891224591412 1.4573613691973 1.45957693065228 1.46400556014702
1 1 1 1
1.47714377581776 1.4799186063176 1.49996708153836 1.5039457897429
1 1 1 1
1.51093217911236 1.52815847611959 1.55215230621511 1.56697853115621
1 1 1 1
1.56971614190741 1.58185560526483 1.58610086516149 1.60152083124652
1 1 1 2
1.60167099340982 1.60536044340423 1.61149457929847 1.62820923524225
1 1 1 1
1.63798993394011 1.63800257492363 1.65599353126218 1.69353486175344
1 1 1 1
1.69864419840162 1.70129405870311 1.7080794657083 1.70834221782386
1 1 1 1
1.73856577704487 1.74286734538365 1.75352596692472 1.76586213258692
1 1 1 1
1.76801662495987 1.77896121796036 1.78259484067046 1.78539266413266
1 1 1 1
1.79091035301485 1.79444988221108 1.8028420970374 1.81901363574158
1 1 1 1
1.82097499800903 1.83786440442691 1.83899864908412 1.83913083829735
1 2 1 1
1.84106676752205 1.86012286021518 1.87087851742921 1.87654300313956
1 1 1 1
1.90021457061565 1.92018958685945 1.9236489507098 1.92529376461198
1 1 1 1
1.92830083026968 1.92994393115026 1.93528639255995 1.93613765548614
1 1 1 1
1.95729837837687 1.96078246230466 1.96685724097516 1.98459427229596
1 1 1 1
1.99788033807904 2.02125852683241 2.02620914704106 2.03340434506273
1 1 1 1
2.03626095761429 2.03677064561267 2.04865363072197 2.04954194478539
1 1 1 1
2.05764204447598 2.06104015166339 2.06924727946458 2.07179067056663
1 1 1 1
2.07571800505294 2.07573210260073 2.09796571451339 2.11486769552448
1 2 1 1
2.12454533431783 2.14424775096643 2.14656827950328 2.14890946199772
1 1 1 1
2.15117564709982 2.1539960919204 2.15617417575337 2.17434220635067
1 1 1 1
2.18799406596593 2.1994437288591 2.20679233692113 2.20692754919319
1 1 1 1
2.21304596197863 2.21337836107097 2.2258352219907 2.24707520491689
1 1 1 1
2.25472838388875 2.26632446993063 2.26971086906431 2.28890118356675
2 1 1 1
2.30028996285762 2.3052873331885 2.32455056487853 2.32834527850804
1 1 1 1
2.33034275949492 2.34385207272674 2.34578561347912 2.34631397824405
3 1 1 1
2.34970771410474 2.35196188034675 2.37351032101775 2.37854663587949
1 1 1 1
2.38486712340511 2.3867962923336 2.39353836574802 2.39862533413314
1 1 1 1
2.4077052369302 2.43042133992784 2.4347191453638 2.43901695079977
1 1 9 1
2.46244728470722 2.46758623023698 2.47170080529608 2.47423617589205
1 1 1 1
2.48203937755313 2.48760023509025 2.49362860003354 2.49802343329229
1 1 1 1
2.4991598640462 2.51342336550002 2.51358844669116 2.51481596421084
1 1 1 1
2.55176128645625 2.55625065866607 2.55743800571582 2.56189370711525
1 1 1 1
2.57699292591033 2.59828464679724 2.61906766850117 2.67120462454102
2 1 1 1
2.69670887595814 2.70334068991957 2.7041290795276 2.70470354816498
1 1 2 1
2.70823019216213 2.72608188637538 2.73631125628313 2.74745300577251
1 1 1 1
2.76657344626814 2.77764685446781 2.77880884215344 2.79435595760341
1 1 1 1
2.79825055926017 2.80068381339022 2.80804511210607 2.82824606354812
1 1 1 1
2.85472517421617 2.86070098597088 2.87232961872088 2.87636576863677
1 1 1 1
2.88186385786217 2.8830740568488 2.89917630269178 2.9027798035896
1 1 1 1
2.90790678303318 2.91235434373815 2.91400911794203 2.92660116755023
1 1 1 1
2.93039559628767 2.9386408866435 2.945425514316 2.95763494095778
1 1 2 1
2.95793672233153 2.98292588281745 3.00491688448974 3.0064752732934
1 1 1 1
3.01475215955936 3.01654288722169 3.0208015806677 3.02486238367861
1 1 1 1
3.03658036908325 3.05200226563628 3.05729115185549 3.08076555003808
1 1 1 1
3.08751738324782 3.09617169500574 3.09797199850578 3.1026995941289
1 1 1 1
3.10845450099364 3.11413278865188 3.15088961463342 3.15117875065401
1 1 1 1
3.15149167587522 3.15759257909201 3.17391178194432 3.18612120673007
1 1 1 1
3.21353034862336 3.21610760145088 3.25925171802641 3.2783308881672
1 1 1 1
3.28259375556649 3.31640705715322 3.31944944134713 3.32498313905811
1 1 1 1
3.32744063920486 3.32771642976241 3.32932250964794 3.3315793100915
1 1 1 1
3.34216957218303 3.34242154495539 3.34271088911103 3.34337679992136
1 1 1 1
3.35126561017592 3.36934045225149 3.37202689885545 3.37255274283399
1 1 1 1
3.38835646972128 3.40257161991408 3.40645288062031 3.41153233300996
1 1 1 1
3.41922633645548 3.41944654901864 3.41990490803005 3.47142322966323
1 1 1 1
3.48533148509903 3.48617348242238 3.49085515413861 3.51596544886987
1 1 1 1
3.5282338911484 3.55518181329576 3.56060619652078 3.57625043670648
1 1 1 1
3.60229105457534 3.60399079029013 3.60864486888651 3.65053160555338
1 1 1 1
3.65252977386568 3.66901718626427 3.68428316254527 3.68433267381138
1 1 1 1
3.69170052539085 3.70113665223498 3.71338782027632 3.72044671795186
1 1 1 1
3.72142818210293 3.73404311399661 3.77630224330033 3.77877128113417
1 1 1 1
3.78076797107481 3.78674962328856 3.78709485417382 3.79395360527857
1 1 2 1
3.80953576202326 3.81068659354995 3.82053328390052 3.82478855597178
1 1 1 1
3.82682064803088 3.83599009750686 3.87029958100203 3.88657995635889
1 1 1 1
3.89869585399125 3.9075414996936 3.91760267333935 3.93816011648463
1 1 1 1
3.95812259493144 3.98371458472476 4.00888809040625 4.01163666632501
1 1 1 1
4.02480543197649 4.02708430349247 4.03293753052936 4.03377358064005
1 1 1 1
4.03864396336903 4.04162889241962 4.0466072109253 4.04661841356993
1 1 1 1
4.04767914628038 4.04800117577427 4.06118812057909 4.06421583742921
1 1 1 1
4.09188792307895 4.103172145632 4.10479602984486 4.11182712447185
1 1 1 1
4.12141118775722 4.12280698476579 4.12966793480824 4.13540591039791
1 1 1 1
4.13575569266997 4.13991043626229 4.14598366264727 4.15010026353818
1 1 1 1
4.15160694876649 4.1537805337125 4.15500995614283 4.17165093816983
1 1 1 1
4.18135560631372 4.18485565132834 4.18940177225258 4.19124130790258
1 1 1 1
4.20309869087374 4.20695937744435 4.20732906330082 4.21198393540346
1 1 1 1
4.21652958435208 4.22045268097424 4.2366403939021 4.2388629545421
1 1 1 1
4.24109217233057 4.25220085979973 4.25573525157659 4.27748236410526
1 1 1 1
4.31299390657706 4.32479457092512 4.32868447365847 4.33682871710489
1 1 1 1
4.35407217573482 4.35520666733998 4.36627826721504 4.36637343174145
1 3 1 1
4.38295168919541 4.40871805682452 4.41676772763432 4.42628260094174
1 1 1 1
4.43447575232511 4.44185783303472 4.44229068343379 4.48825795584601
1 1 1 1
4.49709274237557 4.50002676955416 4.50209368626177 4.52182386310191
1 1 2 1
4.53079212789707 4.5313628974699 4.55132930420894 4.55495879386257
1 1 1 1
4.56196801435067 4.58379758933439 4.59046066820713 4.61162428667891
1 1 1 1
4.61440680984358 4.63967260998531 4.6429065311358 4.65028975436543
2 1 1 1
4.65280911433727 4.65895225882969 4.66461908011646 4.6727049300206
1 1 1 1
4.6753721727072 4.6780901594207 4.69602963402608 4.69774707039145
1 1 1 1
4.69879593901834 4.71429073462435 4.73910559899198 4.74109116821121
1 1 1 1
4.76207964574915 4.79477824370523 4.80850871995124 4.81131239041315
1 1 1 1
4.82046557018559 4.83216132811676 4.84203117982085 4.84357426910859
1 1 2 1
4.85164580071009 4.85263997419144 4.8586394461046 4.86807630977026
1 1 1 1
4.86957483390762 4.87162202545003 4.8759839206379 4.87918135404745
1 1 1 1
4.8939384565786 4.90478431259755 4.91947931191695 4.94831054172878
1 1 1 1
4.95153334582564 4.97859243654453 4.98646570952765 4.99783274592715
1 1 1 1 print(paste("Media:", media))[1] "Media: 266.883928571429"print(paste("Mediana:", mediana))[1] "Mediana: 269.5"print(paste("Moda:", moda))[1] "Moda: 2.4347191453638"print(paste("Varianza:", varianza))[1] "Varianza: 23276.6609219269"print(paste("Desviación Estándar:", desviacion))[1] "Desviación Estándar: 152.566906378569"print(paste("Rango:", rango))[1] "Rango: 1" "Rango: 532"print(paste("Curtosis:", curtosis))[1] "Curtosis: -1.17621642469571"print(paste("Asimetría:", asimetria))[1] "Asimetría: 0.00131602697981087"print("Cuartiles:")[1] "Cuartiles:"print(cuartiles) 25% 50% 75%
136.75 269.50 398.25 print("Percentiles:")[1] "Percentiles:"print(percentiles) 5% 10% 15% 20% 25% 30% 35% 40% 45% 50% 55%
27.95 55.90 81.85 109.80 136.75 163.70 190.65 217.60 244.55 269.50 289.00
60% 65% 70% 75% 80% 85% 90% 95%
315.40 342.35 370.30 398.25 425.20 453.15 479.10 505.05 De este histograma, se infiere que la distribución de esta variable no es normal, y además, está sesgada hacia la derecha.
Como último paso, se realizan algunos análisis bivariados, que como lo indica su nombre, tienen como objetivo explorar las interacciones entre variables a través de gráficos o pruebas analíticas. Por supuesto, esta exploración debe ayudar a responder la pregunta formulada al inicio del EDA, por lo que se utilizarán las variables necesarias para sacar las conclusiones requeridas.
En base a esto, se generan gráficos de barras, diagramas de caja y bigote y dispersión:
library(ggplot2)
library(dplyr)
ggplot(dataset, aes(x = Framework, y = Accuracy, fill = Dataset_Type)) +
geom_bar(stat = "identity", position = "dodge") +
labs(title = "Precisión por Framework y Tipo de Dataset",
x = "Framework", y = "Accuracy") +
theme_minimal()
El gráfico de barras agrupadas, muestra la relación entre las variables Accuracy, Framework y Dataset_Type. Todos los frameworks utilizados presentan una precisión muy similar al trabajar con datos tabulares, situándose alrededor del 0.75-1.00. De este se puede inferir, que ninguno de ellos tiene una ventaja significativa sobre los demás en este tipo de datos; además, debido a su uniformidad, se puede afirmar que los cuatro frameworks son igualmente capaces de capturar la estructura de los datos tabulares, en términos de exactitud.
library(ggplot2)
library(dplyr)
ggplot(dataset, aes(x = Framework, y = Training_Time, fill = Framework)) +
geom_boxplot() +
labs(title = "Tiempo de Entrenamiento por Framework",
x = "Framework", y = "Tiempo de Entrenamiento (s)") +
theme_minimal()
Los diagramas de caja y bigote, muestran la relación entre las variables Training_Time y Framework. Al realizar la comparación con TensorFlow y PyTorch, que presentan tiempos de entrenamiento considerablemente más largos y variables, es evidente que Scikit-learn, ofrece tiempos mucho más eficientes y consistentes. Keras, aunque tiene una mayor variabilidad, también puede ser más eficiente que TensorFlow en ciertos casos. Sin embargo, Scikit-learn es el único framework que logra mantener una precisión alta sin alcanzar un coste significativo de tiempo, lo cual lo convierte en la mejor opción cuando el objetivo es conseguir resultados rápidos y precisos.
Analizando los diagramas con mayor profundidad, se puede afirmar que la mediana baja de Scikit-learn (sesgo positivo) y su menor dispersión (la caja es más estrecha) indican que, en general, este framework ofrece mejores y más rápidos tiempos de entrenamiento. Pues no sólo tiene tiempos más bajos en promedio, sino que estos también son menos variables, y por ende, la probabilidad de obtener tiempos de entrenamiento excesivamente largos, como sucede con TensorFlow o Pytorch, es menor.
library(ggplot2)
library(dplyr)
ggplot(dataset, aes(x = Accuracy, y = Training_Time, color = Framework)) +
geom_point(size = 3) +
labs(title = "Relación entre Precisión y Tiempo de Entrenamiento",
x = "Precisión (Accuracy)", y = "Tiempo de Entrenamiento (s)") +
theme_minimal()
El diagrama de dispersión, muetra la relación entre las variables Training_Time, Accuracy y Framework. En este caso, no se observa una correlación clara entre el tiempo de entrenamiento y la precisión de las IAS. Esto significa que invertir más tiempo en el entrenamiento de una inteligencia artificial, no necesariamente conlleva a un aumento en su precisión. Por lo que optar por frameworks que requieren más tiempo, sin una ganancia clara en precisión, no es nada eficiente y no debe ser el paso a seguir.
Antes de resolver la pregunta final, es importante acotar que toda la información necesaria para la resolución de la misma puede ser inferida a través de los gráficos realizados, por lo que no es necesario recurrir al uso de pruebas analíticas como ANOVA, t de Student, U de Mann- Whitney, Chi-Cuadrado, entre otras.
Ahora si, respondiendo a la pregunta problema, tras haber realizado numerosos análisis a lo largo de este EDA. Se puede afirmar que el framework más adecuado para trabajar con datasets tabulares es Scikit-learn, debido a que este maximiza la eficiencia en términos de tiempo de entrenamiento sin sacrificar precisión. Por lo que es sumamente recomendado para proyectos donde el tiempo de entrenamiento o sus recursos computacionales se conviertan en un factor crítico.